Information processing device, information processing method, and information processing program

Abstract

The present invention provides an information processing device that enables the updating of bookmark information and other data according to the user's usage patterns. [Solution] The system includes a determination unit 4 that acquires bookmark information BK set in multiple information sources used by a user, and access information AC that shows the history of the user's use of each information source, and a determination unit 7 that determines how often to update the bookmark information BK etc. based on the acquired access information AC, and updates the bookmark information BK etc. based on the determination result of the frequency.

Description

Technical Field

[0001] This application belongs to the technical field of information processing apparatuses, information processing methods, and information processing programs. More specifically, it belongs to the technical field of information processing apparatuses and information processing methods for performing processing of presenting bookmark information and the like to a user, and programs for the information processing apparatuses.

Background Art

[0002] In recent years, a great deal of information exists on networks such as the Internet, and research and development have been conducted on techniques for presenting effective information suitable for a user's preferences to the user. As a document showing prior art corresponding to such a situation, for example, Patent Document 1 below can be cited.

[0003] In the prior art disclosed in this Patent Document 1, a "favorite list" is created from Internet addresses and TV program lists that a user frequently accesses. The list in this case is a list of so-called bookmark information. And the user is configured to manually add or delete the corresponding content to and from the favorite list. As a result, the user accesses information on the Internet or the like that suits his or her preferences based on the added or deleted favorite list. Here, the "bookmark information" generally refers to information indicating the location of information on the Internet or TV programs that is expected to be viewed later or frequently because it matches the preferences of the user, and is often character information.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, regarding the prior art disclosed in Patent Document 1, it is generally conceivable that users can collect desired information using multiple apps and websites. In the following description, these apps and websites will be referred to as "information sources." In this case, depending on the user's preferences, access to these multiple information sources or the frequency of access may not be uniform, and there may be bias depending on the information desired. This indicates that there is a bias in the user's level of interest. However, the prior art does not take such bias in the level of interest into consideration, and in this respect, there is room for improvement in the prior art.

[0006] Therefore, this application was made in view of the above-mentioned requests for improvement, and one example of the problem is to provide an information processing device, an information processing method, and a program for said information processing device that enable updating of bookmark information and the like according to the user's usage patterns (i.e., their preferences). [Means for solving the problem]

[0007] To solve the above problems, the invention described in claim 1 includes an acquisition means for acquiring bookmark information set in multiple information sources used by a user, and history information indicating the history of the user's use of each of the information sources; a determination means for determining how often to update bookmark-related information associated with each of the bookmark information based on the acquired history information; and an update means for updating the bookmark-related information based on the determination result of the frequency.

[0008] To solve the above problems, the invention described in claim 6 is an information processing method performed in an information processing apparatus comprising an acquisition means, a determination means, and an update means, the method comprising: an acquisition step of acquiring bookmark information set in a plurality of information sources used by a user and history information indicating the history of the user's use of each of the information sources, respectively, using the acquisition means; a determination step of determining, based on the acquired history information, how often to update bookmark-related information associated with each of the bookmark information, using the determination means; and an update step of updating the bookmark-related information using the update means, based on the determination result of the frequency.

[0009] To solve the above problems, the invention described in claim 7 makes the computer included in the information processing apparatus function as an acquisition means for acquiring bookmark information set in multiple information sources used by a user and history information indicating the history of the user's use of each of the information sources, a determination means for determining how often to update bookmark-related information associated with each of the bookmark information based on the acquired history information, and an update means for updating the bookmark-related information based on the determination result of the frequency. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the outline configuration of the information processing device of the embodiment. [Figure 2] The following are block diagrams showing the general configuration of the information provision system of the embodiment, including the terminal device of the embodiment; (a) is the block diagram, and (b) is a diagram illustrating the recording method of tag information, etc., of the embodiment. [Figure 3] This is a flowchart showing the tag information acquisition process in the example. [Figure 4] These figures illustrate the prompts and responses in the tag information acquisition process of the embodiment, with (a) being Figure (i) and (b) being Figure (ii) which illustrates the same example. [Figure 5] This is a flowchart showing the information presentation process for the example. [Modes for carrying out the invention]

[0011] Next, an embodiment for carrying out the present invention will be described with reference to Figure 1. Figure 1 is a block diagram showing the schematic configuration of the information processing device of the embodiment.

[0012] As shown in Figure 1, the information processing device S of this embodiment is configured to include an acquisition means 4, a determination means 4A, and an update means 7.

[0013] In this configuration, acquisition means 4 acquires bookmark information set in multiple information sources used by the user, and history information showing the user's usage history for each of those information sources.

[0014] The determination means 4A then determines the frequency with which bookmark-related information associated with each bookmark is updated, based on the history information acquired by the acquisition means 4. Based on this, the update means 7 updates the bookmark-related information based on the frequency determination result by the determination means 4A.

[0015] As described above, according to the operation of the information processing device S of the embodiment, the update frequency of bookmark-related information is adjusted for each information source based on the user's usage history for each information source, making it possible to update bookmark-related information in accordance with the user's usage patterns. [Examples]

[0016] Next, specific embodiments corresponding to the above-described embodiments will be explained using Figures 2 to 5. The embodiments described below are examples in which the embodiments are applied to a terminal device that can be connected via a network such as the Internet to a language model system that makes large-scale language models (e.g., LLMs) available on a so-called cloud and provides desired information to the user. The terminal device is a terminal device used by a user (applicant) of the language model system. Specifically, the terminal device is implemented as, for example, a smartphone carried by the user or a personal computer used by the user.

[0017] Furthermore, Figure 2 is a block diagram showing the general configuration of the information provision system of the embodiment, including the terminal device of the embodiment, and Figure 3 is a flowchart of the tag information acquisition process of the embodiment. In addition, Figure 4 is a diagram illustrating the prompts and their responses in the tag information acquisition process of the embodiment, and Figure 5 is a flowchart of the information presentation process of the embodiment. In Figure 2, the same component number as the component in the information processing device S of the embodiment shown in Figure 1 is used for each component of the embodiment that corresponds to each component in the said information processing device S.

[0018] (I) Configuration and Operation of the Information Provision System for the Examples As shown in Figure 2(a), the information provision system SS of the embodiment consists of an embodiment terminal device T used by the user, a language model system 100 that makes the large-scale language model MD available, for example, on a so-called cloud, and the network NW that connects the terminal device T and the language model system 100. The terminal device T consists of an interface 3, a processing unit 10 consisting of a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., an operation unit 11 consisting of operation buttons or a touch panel, etc., a microphone 12, a display 13 consisting of a liquid crystal display, etc., and a speaker 14.

[0019] The processing unit 10 is further composed of a speech acquisition unit 1, a prompt generation unit 2, a determination unit 4, a recording unit 5, an output generation unit 6, and an update unit 7. At this time, the speech acquisition unit 1, the prompt generation unit 2, the determination unit 4, the recording unit 5, the output generation unit 6, and the update unit 7 may be realized by the hardware logic circuit such as the CPU that constitutes the processing unit 10, or may be realized software-wise by the CPU executing a program corresponding to the flowchart showing the tag information acquisition process of the embodiment (see FIG. 3) and the flowchart showing the information presentation process of the embodiment (see FIG. 5). In this case, the program may use the one recorded in the terminal device T in advance, or may use the one acquired each time via the network NW. In the above configuration, the determination unit 4 corresponds to an example of the acquisition means 4 and an example of the determination means 4A of the embodiment, and the update unit 7 corresponds to an example of the update means 7 of the embodiment. Further, as shown by the dashed line in FIG. 2, the determination unit 4 and the update unit 7 constitute an example of the information processing device S of the embodiment.

[0020] In the above configuration, Interface 3 controls the exchange of data and information between the terminal device T and the language model system 100 via the network NW under the control of the processing unit 10. On the other hand, the microphone 12 collects the sound of speech from the user using the terminal device T under the control of the processing unit 10, and outputs the collected result as a sound signal to the speech acquisition unit 1 of the processing unit 10. Thereby, the speech acquisition unit 1 converts the content of the speech into characters based on the sound signal, and outputs the character-converted speech to the prompt generation unit 2 and the recording unit 5. At this time, corresponding to the acquisition of the above speech, the speech acquisition unit 1 acquires date and time information indicating the date and time of the acquisition, position information indicating the geographical position of the acquisition, user identification information for identifying the user who made the speech from other persons, and the like. Here, the above date and time information is acquired from, for example, a timer (not shown) provided in the processing unit 10, and the above position information is acquired from, for example, a position sensor (not shown) provided in the terminal device T (such as a position sensor included in GNSS (Global Navigation Satellite System) or a self-standing position sensor). Also, the above user identification information can be, for example, the one recorded in the recording unit 5 by the user input at the start of using the terminal device T.

[0021] Then, based on the character-converted speech acquired from the speech acquisition unit 1, the prompt generation unit 2 generates a prompt for the example for acquiring the tag information of the example from the language model system 100. At this time, the prompt generation unit 2, from the character-converted speech, in addition to tags such as nouns obtained by the so-called morphological analysis method similar to the conventional one, (i) a tag indicating the context of the content of the speech, (ii) a tag indicating the category (attribute) to which the speech belongs, or (iii) a tag indicating the summary of the speech as a prompt such that the above tag information including the above can be acquired from the language model system 100 (more specifically, from the large language model MD included therein), generates a prompt for the example whose details will be described later, and outputs it to the language model system 100 via the interface 3 and the network NW.

[0022] Next, the language model system 100 that outputs the prompt for the above embodiment outputs response information including tag information for the embodiment corresponding to the prompt for that embodiment. This response information is acquired by the processing unit 10 via the network NW and interface 3. Subsequently, the recording unit 5 of the processing unit 10 associates the utterance output from the utterance acquisition unit 1, the tag information included in the acquired response information, the date and time information, the location information, and the user identification information, etc., and records them non-volatilely.

[0023] As a result, as illustrated in Figure 2(b), the user identification information ID, the utterance V, the date and time information TM, the location information PL, and the tag information TG are associated with each other and non-volatilely recorded as utterance-related tag information 50 for each user and each utterance V. At this time, as illustrated in Figure 2(b), the utterance-related tag information 50 non-volatilely records bookmark information BK, bookmark tag information TGBK, related information IT, and access information AC associated with the user identification information ID. Here, bookmark information BK is bookmark information that the user identified by the user identification information ID has viewed in the past. Bookmark tag information BKTG is tag information that has been assigned to bookmark information BK in the same manner as the method used to assign the tag information TG to the user's utterance. Related information IT is related information (related information that is not bookmark information BK itself) that is related to bookmark information BK, for example, network NW information related to the information contained in bookmark information BK. Furthermore, access information AC is access information that shows the history of the user's past access to the information source corresponding to bookmark information BK.

[0024] Next, the output generation unit 6 of the processing unit 10 generates information to be presented (broadcast) to the user via the speaker 14 based on the speech-related tag information 50 recorded in the recording unit 5, and outputs it to the speaker 14. As a result, the speaker 14, under the control of the processing unit 10, emits a sound corresponding to the information output from the output generation unit 6. If the information is to be presented to the user visually, the output generation unit 6 outputs the information to the display 13. As a result, the display 13, under the control of the processing unit 10, displays an image or the like corresponding to the information output from the output generation unit 6. Furthermore, when an operation necessary to perform the operation of the terminal device T, including the tag information acquisition process and information presentation process of the embodiment, is performed in the operation unit 11, the operation unit 11 generates an operation signal corresponding to the operation and outputs it to the processing unit 10. As a result, the processing unit 10 comprehensively controls each of the above functions of the terminal device T, including the tag information acquisition process and information presentation process of the embodiment, based on the operation signal.

[0025] (II) Regarding the tag information acquisition process in the examples Next, the tag information acquisition process of the embodiment, which is executed mainly by the processing unit 10 of the terminal device T having the configuration described above, will be specifically explained with reference to Figures 2 to 4.

[0026] The tag information acquisition process of the embodiment includes, as shown in Figure 3, a first tag assignment process (see steps S1 to S6 in Figure 3) that assigns the embodiment's tags to the content of the user's speech on the terminal device T, and a second tag assignment process (see steps S10 to S14 in Figure 3) that assigns the embodiment's tags to the content of bookmark information recorded in the recording unit 5 of the terminal device T. Of these, the first tag assignment process starts, for example, when the power switch (not shown) of the terminal device T is turned on. Then, as shown in Figure 3, when the first tag assignment process of the embodiment starts, the processing unit 10 first monitors whether the sound collection result corresponding to the sound of the user's speech has been acquired as an audio signal (step S1). If the audio signal is not acquired in the monitoring in step S1 (step S1: NO), the processing unit 10 moves on to other processing as the terminal device T.

[0027] On the other hand, if the above sound signal is acquired during monitoring in step S1 (step S1: YES), the speech acquisition unit 1 of the processing unit 10 then converts the content of the speech into text based on the sound signal using the same method as before, and outputs the converted speech to the prompt generation unit 2 and the recording unit 5 (step S2). In addition, the speech acquisition unit 1 acquires the above date and time information TM, the above location information PS, and the above user identification information ID, etc., in response to the acquisition of the speech.

[0028] Next, the prompt generation unit 2 generates the prompt of the embodiment based on the transcribed utterance (step S3). At this time, if the user utters an utterance V1 having the content illustrated in the left of Figure 4(a), the prompt generation unit 2 generates the prompt PT1 of the embodiment which includes the utterance V1 and an instruction statement OR1 that requests tag information including a plurality of tags (see (i) above) indicating the context of the content of the utterance V1 from the language model system 100. Subsequently, the prompt generation unit 2 outputs the generated prompt PT1 to the language model system 100 via the interface 3 and the network NW, along with terminal identification information for identifying the terminal device T from other terminal devices (step S4).

[0029] Next, the processing unit 10 determines whether or not it has received response information containing the desired tag information from the language model system 100 corresponding to the prompt PT1 (step S5). If the determination in step S5 is that the response information has not been received (step S5: NO), the processing unit 10 waits until the response information is received. On the other hand, if the determination in step S5 is that the response information has been received (step S5: YES), the recording unit 5 of the processing unit 10 records the tag information contained in the received response information as part of the speech-related tag information 50, associating it with the original utterance V1, the corresponding date and time information TM and location information PS, and the user identification information ID, etc. (step S6. See Figure 2(b)). After that, the processing unit 10 proceeds to the other processing as a terminal device T.

[0030] Here, the tag information that is received as part of the above response information (see step S5: YES) and recorded in association with the utterance V1 (see step S6 above) is, for example, the tag information TG1 containing multiple tags from the embodiment shown on the right of Figure 4(a), which was included in the response information RS1 corresponding to the prompt PT1 shown on the left of Figure 4(a). At this time, when compared with the content of the original utterance V1, the tags [ABC], [Now], and [Perfume] included in the tag information TG1 are tags assigned from the content of the utterance V1 by the above morphological analysis method, and the other tags included in the tag information TG1 are tags assigned to indicate the context of the content of the utterance V1.

[0031] On the other hand, in contrast to the first tagging process of the embodiment described above, the second tagging process of the embodiment obtains bookmark tag information TGBK and related information IT from the language model system 100, which include one or more tags of the embodiment that are to be attached to the bookmark information used in applications used by the user of the terminal device T or on websites on a network NW such as the internet.

[0032] In other words, as shown in Figure 3, as the second tagging process of the embodiment, in parallel with the processing of steps S1 to S6, the processing unit 10 acquires the bookmark information BK via the network NW, for example periodically (step S10). Next, the prompt generation unit 2 generates the prompt of the embodiment based on the acquired bookmark information BK, for example, in accordance with the timing when the bookmark information BK was acquired (step S11). At this time, if the bookmark information BK having the content illustrated in Figure 4(b) left is acquired and includes character information, the prompt generation unit 2 generates a prompt PT2 that includes the bookmark information BK, an instruction statement OR2 that requests the language model system 100 to provide bookmark tag information TGBK including related information IT containing a summary of the content of the bookmark information BK and a plurality of tags (see (i) above) indicating the context of the summary. Subsequently, the prompt generation unit 2 outputs the generated prompt PT2 together with the terminal identification information to the language model system 100 via the interface 3 and the network NW (step S12).

[0033] Next, the processing unit 10 determines whether or not it has received response information containing the desired bookmark tag information TGBK from the language model system 100 corresponding to the prompt PT2 (step S13). If, in the determination in step S13, the response information is not received (step S13: NO), the processing unit 10 waits until the response information is received. On the other hand, if, in the determination in step S13, the response information is received (step S13: YES), the recording unit 5 of the processing unit 10 records the bookmark tag information TGBK and related information IT contained in the received response information as part of the speech-related tag information 50, associating them with the original bookmark information BK and user identification information ID (step S14; see Figure 2(b)). At this time, the processing unit 10 may also record the date and time information TM and location information PS corresponding to the bookmark tag information TGBK as well.

[0034] Here, the bookmark tag information TGBK, which is received as part of the above response information (see step S13: YES) and recorded in association with the bookmark information BK (see step S14 above), is the bookmark tag information TGBK shown on the right in Figure 4(b) that was included in the response information RS2 corresponding to the prompt PT2 shown on the left in Figure 14(b), and is recorded together with the summary text as related information IT. At this time, when compared with the content of the original bookmark information BK and the content of related information IT (summary text), the tags [perfume] and [fashion] included in the bookmark tag information TGBK are tags assigned by the above morphological analysis method from the content of the bookmark information BK or the content of related information IT, and the other tags included in the bookmark tag information TGBK are tags assigned to indicate the context of the content of the bookmark information BK or the content of related information IT. After that, the processing unit 10 proceeds to the above other processing as a terminal device T.

[0035] (III) Information presentation process for the examples Next, the information presentation process of an embodiment, which is executed primarily by the processing unit 10 of the terminal device T, will be specifically explained using Figure 5.

[0036] The information presentation process in the embodiment is started, for example, at predetermined intervals or by a user's start operation. When the information presentation process in the embodiment is started, as shown in Figure 5, the determination unit 4 of the processing unit 10 refers to the speech-related tag information 50 (see Figure 2(b)) identified by the user's user identification information ID and obtains the bookmark information BK and access information AC recorded therein (step S20). Next, the determination unit 4 determines the frequency of access to the information source for the simultaneously obtained bookmark information BK, as indicated by the obtained access information AC, and outputs the determination result to the update unit 7. As a result, the update unit 7 updates the bookmark information BK and related information IT (hereinafter, bookmark information BK and related information IT are simply referred to as "bookmark information BK, etc.") by increasing the update frequency, for example, the higher the access frequency indicated by the access information AC (step S21).

[0037] Next, the output generation unit 6 determines whether the access frequency is higher than a preset threshold (step S22). If the determination in step S22 indicates that the access frequency is higher than the threshold (step S22: YES), the output generation unit 6 presents the updated bookmark information BK, etc. (see step S21) to the user of the terminal device T via audio output through the speaker 14 or image output through the display 13 (step S23). Subsequently, the processing unit 10 determines whether to terminate the information presentation process of the embodiment, for example, if an operation to terminate the information presentation process of the embodiment is performed on the operation unit 11 (step S24). If the determination in step S24 indicates that the information presentation process of the embodiment should be terminated (step S24: YES), the processing unit 10 terminates the information presentation process. On the other hand, if the determination in step S24 indicates that the information presentation process of the embodiment should be continued (step S24: NO), the processing unit 10 returns to step S20 and continues the series of information presentation processes described above.

[0038] On the other hand, if the access frequency indicated by the access information AC in the determination in step S21 is less than or equal to the threshold (step S22: NO), the processing unit 10 compares the tags included in the recorded tag information TG1 (see Figure 3 step S6, Figure 4(a)) (tags attached to the user's utterance) with the tags included in the recorded bookmark tag information TGBK (see Figure 3 step S14, Figure 4(b)) (tags attached to the bookmark information BK), and determines whether or not an utterance has been made by a user to whom tag information TG1 has been attached, in which one or more tags match the tags included in the bookmark tag information TGBK (step S25). If, in the determination in step S25, there is no utterance by a user to whom tag information TG1 has been attached (step S25: NO), the processing unit 10 proceeds to the process in step S24. On the other hand, in the determination in step S25, if the user to whom the tag information TG1 is assigned makes a statement (step S25: YES), the processing unit 10 proceeds to step S23 in accordance with the timing of the statement and presents the bookmark information BK etc. to the user (step S23), and then proceeds to the processing in step S24.

[0039] As explained above, according to the tag information acquisition process and information presentation process of the embodiment, the update frequency of bookmark information BK, etc. is adjusted for each information source based on the user's access frequency (i.e., usage history) for each information source (see steps S21 and S22 in Figure 5), making it possible to update bookmark information BK, etc. in accordance with the user's usage patterns.

[0040] Furthermore, based on the acquired access information AC, the more frequently a user accesses each information source, the more frequently the bookmark-related information acquired from that information source is updated (see Figure 5, step S21). This makes it possible to update bookmark information BK and other information in accordance with the user's usage patterns for each information source.

[0041] Furthermore, since the frequency of presenting updated bookmark information BK, etc., is controlled based on the determination result of the update frequency of the bookmark information BK, etc. itself (see steps S22 and S23 in Figure 5), it becomes possible to present bookmark information BK, etc., to the user in a way that is even more tailored to the user's usage patterns.

[0042] Furthermore, when the update frequency is below a predetermined threshold frequency (see step S22: NO), the bookmark information BK, etc., is presented at the time the user makes a statement corresponding to the bookmark information BK, etc. (see Figure 5, steps S25: YES and S23), making it possible to present bookmark information BK, etc., to the user in a way that is even more tailored to the user's usage pattern.

[0043] Furthermore, since the information source is the app used by the user or the website they visit, and the access information AC indicates the user's usage history of the app or browsing history of the website, it becomes possible to update bookmark information BK and other data to better match the user's usage patterns.

[0044] In the embodiments described above, the system was configured to assign tags to user utterances as input. However, it is also possible to configure the system to assign tags to images taken by the user or to text itself, such as notes written by the user, as input.

[0045] Furthermore, it is possible to record a program corresponding to the flowcharts shown in Figures 3 and 5 onto a recording medium such as an optical disc or hard disk, or to obtain it via a network such as the Internet, and then read and execute it on a general-purpose microcomputer, thereby making the microcomputer function as the processing unit 10 of the embodiment. [Explanation of symbols]

[0046] 4 Acquisition means (judgment part) 4A Judgment means 7 Update means (update section) S Information Processing Device T terminal device SS Information Provision System V1 Utterance OR1, OR2 instructions PT1, PT2 prompt RS1, RS2 response information TG1 Tag Information TGBK Bookmark Tag Information IT-related information

Claims

1. Acquisition means for acquiring bookmark information set in multiple information sources used by a user, and history information showing the user's usage history for each of the said information sources, A determination means for determining the frequency of updating bookmark-related information associated with each bookmark based on the acquired history information, Based on the frequency determination result, an update means for updating the bookmark-related information, An information processing device characterized by comprising:

2. In the information processing apparatus according to claim 1, The determination means is characterized by determining, based on each of the acquired history information, that the more frequently the user uses each of the information sources, the higher the update frequency of the bookmark-related information acquired from each information source.

3. In the information processing apparatus according to claim 1 or claim 2, A presentation means for presenting the updated bookmark-related information to the user, Based on the determination result, a control means controls the frequency of presentation of the bookmark-related information by the presentation means, An information processing device characterized by further comprising the following:

4. In the information processing apparatus described in claim 3, The information processing apparatus is characterized in that, when the determined update frequency is less than or equal to a preset threshold frequency, the presentation means controls the presentation of the bookmark-related information to occur at the time when the user inputs content corresponding to the bookmark-related information.

5. In the information processing apparatus according to claim 1, The aforementioned information source is an application used by the user or a website viewed by the user. The information processing device is characterized in that the history information indicates the usage history of the application by the user or the browsing history of the website by the user.

6. An information processing method performed in an information processing apparatus comprising an acquisition means, a determination means, and an update means, An acquisition step of acquiring, by means of the acquisition means, bookmark information set in multiple information sources used by the user and history information showing the user's usage history of each of the said information sources, A determination step in which the determination means determines the frequency at which bookmark-related information associated with each bookmark is updated based on each of the acquired history information, An update step in which the bookmark-related information is updated by the update means based on the frequency determination result, An information processing method characterized by including

7. The computer included in the information processing device Acquisition means for acquiring bookmark information set in multiple information sources used by a user, and history information showing the user's usage history for each of the said information sources, A determination means for determining the frequency of updating bookmark-related information associated with each bookmark based on the acquired history information, and Based on the results of the frequency determination, an update means updates the bookmark-related information. An information processing program characterized by functioning as such.

Images