Analysis device

Abstract

An analysis device comprises: a storage unit for storing an input statement and information that distinguishes a user in association with each other; an extraction unit for extracting, on a corresponding function basis for each user, input statements stored in the storage unit; a classification unit for classifying, by function, input statements into intra-user similarity groups for each user such that the input statements extracted by the extraction unit form an intra-user similarity group composed of mutually similar input statements; an aggregation unit for aggregating, on a function-by-function basis, the intra-user similarity groups between users such that the intra-user similarity groups form an inter-user similarity group composed of mutually similar intra-user similarity groups; and an output unit for outputting a result of aggregation by the aggregation unit.

Description

[Technical field]

[0001] One aspect of the present disclosure relates to an analysis device. [Background technology]

[0002] Conventionally, there is known a dialogue system that acquires an input sentence in natural language input by a user and executes a function according to the input sentence. In addition, in such a dialogue system, a mechanism is known that presents an example of an input sentence to a user to support the user's operation. For example, Patent Document 1 selects a function based on a usage history of executing the function by voice. Patent Document 1 presents an example of an input sentence associated with the selected function to the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-134675 A Summary of the Invention [Problem to be solved by the invention]

[0004] In a dialogue system that executes a function based on a natural sentence input by a user, various natural sentences may be used to execute the same function. Therefore, when presenting examples of input sentences to a user, it is desirable to present input sentences that the user would like to use. However, in the above dialogue system, since input sentences that are linked to functions in advance are presented, the presented input sentences may not be examples that many users would like to use.

[0005] An object of one aspect of the present disclosure is to provide an analysis device capable of acquiring an input sentence that is used by many users. [Means for solving the problem]

[0006] An analysis device according to one aspect of the present disclosure is a device that analyzes an input sentence input into a terminal device capable of executing a function corresponding to a user's input sentence, and includes a memory unit that links and stores the input sentence with information that distinguishes the user, an extraction unit that extracts the input sentences stored in the memory unit on a user-by-user basis for each corresponding function, a classification unit that classifies the input sentences into intra-user similar groups by function on a user-by-user basis so that the input sentences extracted by the extraction unit form intra-user similar groups composed of input sentences that are similar to each other, an aggregation unit that aggregates intra-user similar groups by function between users so that the intra-user similar groups form inter-user similar groups composed of intra-user similar groups that are similar to each other, and an output unit that outputs the aggregation results by the aggregation unit.

[0007] In the above analysis device, input sentences are aggregated to form inter-user similarity groups for each function, which are composed of intra-user similarity groups that are similar to each other. The intra-user similarity groups are formed based on input sentences classified by user. That is, the input sentences that constitute one intra-user similarity group are input by one user. Therefore, the number of intra-user similarity groups that constitute a inter-user similarity group is the number of users who use the input sentences that constitute the inter-user similarity group. It can be said that an inter-user similarity group composed of many intra-user similarity groups includes input sentences used by many users. Therefore, by using the aggregation result by the aggregation unit, input sentences used by many users can be obtained. Effect of the Invention

[0008] According to one aspect of the present invention, it is possible to provide an analysis device capable of acquiring input sentences that are used by many users. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating a functional configuration of an analysis system including an example analysis device. [Diagram 2] FIG. 13 is a diagram showing an example of a reception screen presented to a user on a user terminal. [Diagram 3] FIG. 11 is a diagram showing an example of a usage history. [Figure 4] FIG. 13 is a diagram illustrating an extraction result by an extraction unit. [Diagram 5] FIG. 4 is a diagram illustrating a classification result by a classification unit. [Figure 6] 13 is a diagram illustrating a result of aggregation of intra-user similar groups by an aggregating unit. FIG. [Figure 7] FIG. 11 is a diagram illustrating an example of an aggregated result output by an output unit. [Figure 8] 10 is a flowchart showing an example of the operation of the analysis device. [Figure 9] FIG. 2 illustrates an example of a hardware configuration of an analysis device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or corresponding elements are denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] FIG. 1 is a diagram showing a functional configuration of an analysis system 1 including an analysis device 10 according to an example. The analysis system 1 includes the analysis device 10 and a plurality of user terminals (terminal devices) 20. The analysis device 10 is, for example, a server device configured to be able to communicate with the user terminal 20. The analysis device 10 may be configured by one device or may be configured by a plurality of devices. The user terminal 20 is, for example, a computer operated by a user. As an example, there is a one-to-one correspondence between a user and the user terminal 20. The user terminal 20 is a smartphone owned by the user. However, the form of the user terminal 20 is not limited to a specific form. Other examples of the user terminal 20 include a tablet terminal, a wearable terminal, a personal computer, a smart speaker, a smart TV, a smart home appliance, and the like. In addition, one user terminal 20 may be shared by a plurality of users.

[0012] The user terminal 20 has a function of providing a dialogue system (virtual assistant, artificial intelligence assistant, digital assistant, personal assistant) to the user. The dialogue system is a system that accepts an input sentence entered by the user and presents to the user the execution result of a function according to the user's intention estimated from the input sentence.

[0013] For example, when the user inputs an input sentence such as "Tell me how to get to Tokyo Station," the dialogue system launches a route search application based on the analysis result of the input sentence, and presents the user with a route to Tokyo Station. The user terminal 20 has known functions for executing such a dialogue system. For example, the user terminal 20 has a function for accepting an input sentence, a function for analyzing the input sentence by morphological analysis or the like, a function for launching a function corresponding to the content of the input sentence according to the analysis result of the input sentence (for example, a function of an application installed in the user terminal 20), and a function for presenting the execution result of the function to the user.

[0014] The user terminal 20 may not have all the functions described above. For example, some functions (for example, a function to analyze an input sentence) may be executed by a first device configured to be able to communicate with the user terminal 20 and different from the user terminal 20. In this case, for example, the user terminal 20 may transmit the input sentence to the first device and receive the result of analysis by the first device from the first device. Also, the function specified according to the analysis result (the function corresponding to the input sentence) may not necessarily be executed on the user terminal 20. The function specified according to the analysis result may be executed on a second device configured to be able to communicate with the user terminal 20 and different from the user terminal 20. In this case, for example, the user terminal 20 may obtain the execution result of the function corresponding to the input sentence from the second device and present the execution result to the user. Note that the first device and the second device may be the same device or may be different devices from each other. Also, the analysis device 10 may function as a part or all of the above-mentioned first device and / or second device.

[0015] FIG. 2 is a diagram showing an example of a reception screen presented to a user via the user terminal 20 in the above-mentioned dialogue system. For example, a plurality of icons on a menu screen are displayed on the display of the user terminal 20. The reception screen P is started when an icon corresponding to the dialogue system is selected by a touch operation or the like by the user. As shown in FIG. 2, the reception screen P displays a system message M of "What can I do for you?" along with an example sentence E which is an example of an input sentence. In the example of FIG. 2, four example sentences E of "Tell me some recommended information," "I want to find a member," "Read a book," and "Is the train late?" are presented to the user.

[0016] With the dialogue system running, the user can input an input sentence. For example, the user may input an input sentence in text format by inputting text into a text input window T arranged at the bottom of the reception screen P. The user may also input an input sentence in the form of voice data by performing voice input using a voice reception function. The voice reception function is activated by selecting a voice input icon V arranged to the right of the text input window T. In this case, the input sentence is converted into text format by a voice recognition technique. The user may also input an input sentence by selecting a desired example sentence from the example sentences E presented on the reception screen P by a touch operation or the like. In this way, the method of inputting an input sentence in the user terminal 20 is not limited.

[0017] The reception screen P in Fig. 2 shows a state in which the input sentence S "Is the train late?" has been input to the user terminal 20 by the user through the above series of processes. That is, it shows a case in which "Is the train late?", one of the example sentences E presented on the reception screen P, has been used (adopted) by the user. After this, the input sentence S is analyzed, and a function corresponding to the input sentence S is provided to the user. In this way, by presenting an appropriate example sentence E to the user, it is possible to encourage the user to use the dialogue system.

[0018] In a dialogue system, by presenting example sentences that many users would like to use, users can be effectively encouraged to use the dialogue system. Thus, an example analysis system 1 has a function of extracting example sentences that many users use. By referring to example sentences that are actually used by many users, the dialogue system can present example sentences that are likely to be used by users. Such an analysis system 1 will be further described below.

[0019] The user terminal 20 includes a transmission unit 21 and an example sentence display unit 22. The transmission unit 21 transmits a usage history of the dialogue system by the user to the analysis device 10. The usage history is history information for each user that includes information indicating a function corresponding to an input sentence and information indicating a time point when the function was executed. When using the dialogue system, the user may register attribute information such as his / her date of birth and gender in the dialogue system.

[0020] FIG. 3 is a table showing an example of the usage history of a plurality of user terminals 20 received by the analysis device 10. In the example of FIG. 3, usage history of each user terminal 20 owned by four users whose user IDs are U1, U2, U3, and U4, respectively, is shown. One record (one row) of the table shown in FIG. 3 corresponds to one usage history. The usage history may be a history corresponding to one use of the dialogue system. The usage history includes, for example, a "user ID", a "date and time", an "input sentence", a "function", and a "function ID". The "user ID" is information for distinguishing users who have used the dialogue system from each other. The "user ID" is, for example, identification information for uniquely identifying a user. The "user ID" can be identified, for example, based on the user's account information stored in the user terminal 20. The "date and time" is information indicating the time when a function corresponding to an input sentence is executed. Note that the time when a function corresponding to an input sentence is executed is not particularly required to be punctual. For example, the time when the function corresponding to the input sentence is executed may be the time when the input sentence is input (the start time of the process for executing the function corresponding to the input sentence), or the time when the execution result of the function corresponding to the input sentence is presented to the user (the end time of the above process). The "input sentence" is information indicating the content of the input sentence input by the user. As an example, the input sentence is composed of text data. The "function" is information indicating the name of the function corresponding to the input sentence input by the user (for example, a pre-registered application name, etc.). In other words, the "function" is the name of the function executed by the dialogue system when the user inputs the input sentence. The "function ID" is identification information for uniquely identifying this "function". In addition, when the attribute information of the user is registered when using the dialogue system, the usage history may include the attribute information of the user.

[0021] The example sentence display unit 22 is a functional unit that presents example sentences to the user. As shown in FIG. 2, the example sentence display unit 22 in one example displays an example sentence E on a reception screen P (a screen waiting for an input from a user) immediately after the dialogue system is started. In one example, the example sentence E may be transmitted from the analysis device 10 to the user terminal 20. In that case, the example sentence display unit 22 displays the example sentence E received from the analysis device 10. Also, the example sentence E may be transmitted to the user terminal 20 from a device that manages the dialogue system and is provided separately from the analysis device 10. Also, multiple types of example sentences may be prepared in accordance with the attribute information of the user. For example, when different example sentences are prepared according to age, sex, etc., the example sentence display unit 22 may refer to the attribute information of the user and present the example sentence that matches the attribute information to the user.

[0022] The analysis device 10 includes a receiving unit 11, a usage history database (usage history DB) 12, an extracting unit 13, a classifying unit 15, an aggregating unit 16, and an output unit 17. In the analysis device 10 as an example, input sentences input by the same user form similar groups that are similar to each other, and similar groups between different users that are similar to each other are aggregated. This makes it possible to obtain a set of similar input sentences input by different users and the number of similar groups (i.e., the number of users) that constitute the set. The analysis device 10 will be described in detail below.

[0023] The receiving unit 11 receives a usage history (see FIG. 3) from each user terminal 20. For example, the receiving unit 11 periodically receives the usage history from each user terminal 20, thereby periodically collecting the usage history accumulated in each user terminal 20. The usage history received by the receiving unit 11 is stored in a usage history DB (storage unit) 12. The usage history DB 12 is a database that accumulates usage history. The usage history stored in the usage history DB 12 from the receiving unit 11 includes data of an input sentence linked to information that distinguishes a user, and a function corresponding to the input sentence. In one example, the usage history received from each user terminal 20 is accumulated in the usage history DB in its original format.

[0024] The extraction unit 13 extracts input sentences stored in the usage history DB 12 for each corresponding function on a user-by-user basis. FIG. 4 shows a schematic diagram of the extraction result of the usage history by the extraction unit. In the example of FIG. 4, the extraction result of the usage history of the first user and the usage history of the second user is shown for the sake of simplicity. The first user (user ID is U1) inputs input sentences such as "Today's weather", "What's the weather today", "Tell me the weather today", "Do I need an umbrella", and "Do you need an umbrella" into the user terminal in order to activate a weather-related function using the dialogue system, and inputs input sentences such as "Alarm" and "Set an alarm" into the user terminal in order to activate an alarm-related function. The second user (user ID is U2) inputs input sentences such as "Today's weather" and "Tell me the weather today" into the user terminal in order to activate a weather-related function, and inputs input sentences such as "Wake me up at 8 o'clock" and "Alarm clock" into the user terminal 20 in order to activate an alarm-related function. As shown in FIG. 4, the extraction unit 13 organizes the input sentences extracted on a user-by-user basis by function. In the following description, a user with a user ID U1 may be referred to as user U1, and a user with a user ID U2 may be referred to as user U2.

[0025] In order to extract examples of frequently used input sentences, the extraction unit 13 may extract only input sentences corresponding to functions executed more frequently than a set criterion in a set period. In this case, the extraction criterion may be the number of days each function was executed. For example, the extraction unit 13 may extract only input sentences corresponding to functions executed by a user on a predetermined number of days (e.g., five days) or more in a predetermined period (e.g., one month). The extraction criterion may also be the number of times each function was executed. For example, the extraction unit 13 may extract only input sentences corresponding to functions executed by a user on a predetermined number of times (e.g., ten times) or more in a predetermined period (e.g., one month).

[0026] In addition, the extraction unit 13 may extract a usage history for each user who satisfies a specific condition based on the attribute information of the user. For example, the extraction unit 13 may divide users into a plurality of categories based on conditions such as age, sex, etc., and extract a usage history of a user corresponding to each divided category. In one example, the extraction unit 13 may divide users by attributes, such as men in their 20s, women in their 20s, men in their 30s, women in their 30s, etc., and extract a usage history for each divided attribute.

[0027] The classification unit 15 classifies the input sentences into groups by function for each user so that the input sentences extracted by the extraction unit 13 form groups (intra-user similar groups) composed of input sentences similar to each other. For example, the classification unit 15 acquires input sentences for each function for each user ID. Next, the classification unit 15 derives the similarity of character strings between the acquired input sentences. For example, the classification unit 15 may derive features of each input sentence and calculate the similarity between the derived features. As an example, the classification unit 15 divides the input sentence into words by morphological analysis, and calculates the similarity between the features by using a set of words (bag of words) as a feature (vector). The similarity may be, for example, cosine similarity. Then, the classification unit 15 groups the input sentences so that the groups form groups whose similarity to each other is equal to or greater than a predetermined threshold.

[0028] FIG. 5 is a schematic diagram showing the classification result of the intra-user similar group by the classification unit. In FIG. 5, the extraction result of FIG. 4 is classified into intra-user similar groups. In the example shown in FIG. 5, "Today's weather", "What's the weather today", "Tell me the weather today", "Do I need an umbrella", and "Do I need an umbrella" which are linked to user U1 and extracted as input sentences corresponding to the weather are grouped into an intra-user similar group U1001A consisting of "Today's weather", "What's the weather today" and "Tell me the weather today", and an intra-user similar group U1001B consisting of "Do I need an umbrella" and "Do I need an umbrella". Similarly, "Alarm" and "Set alarm" which are linked to user U1 and extracted as input sentences corresponding to an alarm are grouped into an intra-user similar group U1015A, and "Today's weather" and "Tell me the weather today" which are linked to user U2 and extracted as input sentences corresponding to the weather are grouped into an intra-user similar group U2001A. Each intra-user similar group may be linked to a corresponding user ID and function ID.

[0029] In addition, when the extraction unit 13 extracts the usage history for each user who satisfies a specific condition based on the attribute information of the user, the classification unit 15 may classify the input sentence based on the usage history extracted for each specific condition. That is, the classification unit 15 may obtain a classification result for each specific condition.

[0030] The aggregation unit 16 aggregates intra-user similar groups by function between users so that the intra-user similar groups classified by the classification unit 15 by user unit form inter-user similar groups composed of intra-user similar groups similar to each other. For example, the aggregation unit 16 acquires intra-user similar groups grouped by user ID for each function. Next, the aggregation unit 16 combines all input sentences belonging to each intra-user similar group to generate one sentence (combined sentence) for each intra-user similar group. Then, the aggregation unit 16 forms an inter-user similar group based on the similarity between the combined sentences formed for each intra-user similar group. The similarity between the combined sentences of the intra-user similar groups belonging to the same inter-user similar group is equal to or greater than a predetermined threshold. That is, the aggregation unit 16 groups intra-user similar groups into inter-user similar groups so that the similarity between the combined sentences belonging to the same inter-user similar group is equal to or greater than a predetermined threshold. Note that the method of deriving the similarity, the criterion for grouping, and the like may be the same as the method of deriving the similarity in the classification unit, and may be different.

[0031] FIG. 6 is a schematic diagram showing the aggregation result of the intra-user similarity group by the aggregation unit 16. In FIG. 6, the classification result of FIG. 5 is aggregated as an inter-user similarity group. In the example shown in FIG. 6, an intra-user similarity group U1001A associated with and classified as a user U1 and an intra-user similarity group U2001A associated with and classified as a user U2 constitute an inter-user similarity group G001A that are similar to each other. In addition, an intra-user similarity group U1001B associated with and classified as a user U1 constitutes an inter-user similarity group by itself since there is no similar intra-user similarity group. Similarly, an intra-user similarity group U1015A, an intra-user similarity group U2015A, and an intra-user similarity group U2015B also constitute an inter-user similarity group G015A, an inter-user similarity group G015B, and an inter-user similarity group G015C, respectively.

[0032] The aggregation unit 16 also calculates the number of intra-user similar groups constituting the aggregated intra-user similar group as the number of users. For example, in the example of Fig. 6, the intra-user similar group G001A is composed of intra-user similar groups U1001A and U2001A, so the number of users using the input sentence corresponding to the intra-user similar group G001A is calculated as "2". The inter-user similar groups G001B, G015A, G015B, and G015C are each composed of one intra-user similar group, so the number of users is calculated as "1" for each of them.

[0033] In addition, when the classification unit 15 classifies the input sentences based on the usage history extracted for each specific condition, i.e., when the classification result is obtained for each specific condition, the aggregating unit 16 may aggregate intra-user similar groups based on the classification result obtained for each specific condition.

[0034] The output unit 17 outputs the aggregation result by the aggregation unit 16. FIG. 7 is a diagram showing an example of the aggregation result. As shown in FIG. 7, the aggregation result includes a function, an input sentence constituting a user similarity group corresponding to the function, and the number of users using the input sentence. In the aggregation result, the corresponding functions, input sentences, and number of users are linked to each other. The aggregation result may include the total number of users for each function. For example, the aggregation unit 16 may extract records linked to the same function ID, and count the user IDs included in the extracted records while removing duplicates, thereby deriving the total number of users who input the input sentences corresponding to each function.

[0035] In one example, the output unit 17 may output input sentences used by many users as example sentences to the user terminal 20. For example, the output unit 17 selects example sentences from the input sentences constituting the inter-user similarity groups in descending order of the number of users, and outputs the selected example sentences to the user terminal 20. The example sentences may be selected, for example, randomly from the input sentences constituting the inter-user similarity groups. When the aggregation unit 16 aggregates the intra-user similarity groups based on the classification results acquired for each specific condition, the output unit 17 may output multiple types of example sentences for each specific condition.

[0036] In another example, an example sentence may be selected from the input sentences by an administrator of the analysis device 10 based on the output result output by the output unit 17. For example, the administrator may select an input sentence suitable as an example sentence from the input sentences constituting the user similarity group corresponding to the desired function while referring to the calculated number of users. The selected input sentence may be registered in the dialogue system as example sentence E. The administrator may create a new example sentence by referring to the output result. For example, the administrator may create an example sentence such as "Wake me up at XX o'clock" by referring to the input sentence "Wake me up at 8 o'clock."

[0037] Next, an example of the operation of the extraction unit 13, the classification unit 15, and the aggregation unit 16 of the analysis device 10 will be described with reference to the flowchart shown in Fig. 8. That is, the flowchart in Fig. 8 is based on the premise that the usage history transmitted from the transmission unit 21 of the user terminal 20 to the reception unit 11 of the analysis device 10 is accumulated in the usage history DB 12.

[0038] First, the extraction unit 13 extracts input sentences from the usage history DB 12 (step S1). In step S1, the input sentences are extracted for each function on a user-by-user basis. That is, the extracted input sentences are linked to at least a user ID and a function. Next, the classification unit 15 classifies the input sentences (step S2). In step S2, the input sentences are classified into intra-user similar groups for each function on a user-by-user basis. For example, the classified input sentences may be linked to identification information that identifies the intra-user similar groups. Next, the aggregation unit 16 aggregates the intra-user similar groups into inter-user similar groups (step S3). For example, the intra-user similar groups may be linked to identification information that identifies the inter-user similar groups. Next, the aggregation unit 16 calculates the number of intra-user similar groups constituting the inter-user similar groups as the number of users (step S4). For example, the aggregation unit 16 may calculate the number of intra-user similar groups linked to the inter-user similar groups as the number of users.

[0039] As described above, in the analysis device 10, input sentences input by a plurality of users are aggregated to form a user-to-user similarity group for each function. This user-to-user similarity group is composed of one or more intra-user similarity groups. One intra-user similarity group is a collection of mutually similar input sentences among input sentences input by one user corresponding to a function. In other words, one intra-user similarity group corresponds to one user. Therefore, an inter-user similarity group composed of many intra-user similarity groups includes mutually similar input sentences used by many users. Therefore, by using the aggregation result by the aggregation unit, input sentences used by many users can be acquired. An input sentence actually used by many users is highly likely to be an input sentence that other users would like to use. Therefore, based on the acquired input sentences, example sentences that are likely to be used by users can be displayed.

[0040] Therefore, in the analysis system 1, the aggregating unit 16 calculates information including the number of intra-user similar groups that make up the inter-user similar group as the aggregation result. The number of intra-user similar groups that make up the inter-user similar group corresponds to the number of users who use the input sentences that make up the inter-user similar group. By deriving the number of users by the aggregating unit 16, it is possible to easily obtain input sentences that are actually used by many users.

[0041] In one example, the extraction unit 13 extracts input sentences corresponding to functions that have been executed more times than a set criterion in a set period. For example, the criterion extracted by the extraction unit 13 is the number of days each function has been executed. In this way, by setting the number of days executed by a user in a specified period as a threshold, input sentences corresponding to functions that the user uses on a daily basis can be efficiently extracted. Furthermore, when the number of times executed by a user in a specified period is set as a threshold, input sentences that have suddenly become popular among users can be efficiently extracted. Furthermore, by limiting the number of input sentences extracted by the extraction unit 13, the computation load on the analysis device 10 can be reduced.

[0042] In one example, the usage history DB12 stores user attribute information linked to input sentences, and the aggregation unit 16 aggregates intra-user similar groups by function between users who have at least a portion of the attribute information that matches. In this configuration, input sentences that are used by a large number of users can be obtained for each user attribute. For example, when intra-user similar groups between users who have attributes of age in their 30s and gender as male are aggregated by function, input sentences that are frequently used by men in their 30s can be obtained. This makes it possible to generate example sentences that are suitable for the user attributes.

[0043] Although an example has been described in which the user's attribute information is date of birth, gender, etc., the attribute information may be other information associated with the user, such as location information, hobbies, preferences, health condition, etc. For example, when the attribute information includes location information, an input sentence input within a predetermined range such as a tourist spot may be extracted by the extraction unit. In this case, input sentences that are frequently input within the predetermined range can be presented to a user (user terminal) who has visited the predetermined range.

[0044] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. The method of realizing each functional block is not particularly limited. That is, each functional block may be realized by using one device that is physically or logically combined, or may be realized by using two or more devices that are physically or logically separated and directly or indirectly connected (for example, by wire, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

[0045] Functions include, but are not limited to, judging, determining, assessing, calculating, processing, deriving, investigating, searching, verifying, receiving, sending, outputting, accessing, resolving, selecting, choosing, establishing, comparing, anticipating, expecting, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning.

[0046] For example, the analysis device 10 according to an embodiment of the present disclosure may function as a computer that performs the communication control method of the present disclosure. Fig. 9 is a diagram showing an example of a hardware configuration of the analysis device 10 according to an embodiment of the present disclosure. The above-mentioned analysis device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0047] In the following description, the term "apparatus" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the analysis apparatus 10 may be configured to include one or more of the devices shown in FIG. 1, or may be configured to exclude some of the devices.

[0048] Each function in the analysis device 10 is realized by loading a specific software (program) onto hardware such as a processor 1001 and a memory 1002, causing the processor 1001 to perform calculations, control communications via a communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and the storage 1003.

[0049] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like.

[0050] Moreover, the processor 1001 reads out a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to the read out programs. As the program, a program that causes a computer to execute at least a part of the operations described in the above-mentioned embodiment is used. For example, the aggregation unit 16 may be realized by a control program stored in the memory 1002 and operating in the processor 1001, and other functional blocks may be similarly realized. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunication line.

[0051] The memory 1002 is a computer-readable recording medium, and may be configured by at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store a program (program code), software modules, etc. that are executable to implement a communication control method according to an embodiment of the present disclosure.

[0052] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. Storage 1003 may be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0053] The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0054] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0055] In addition, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0056] Furthermore, the analysis device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc., and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0057] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented as a modified or altered form without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0058] The order of the steps, sequences, flow charts, etc. of each aspect / embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0059] The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

[0060] The determination may be based on a value represented by a single bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0061] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched according to execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

[0062] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0063] Additionally, software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired and / or wireless technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave, etc.), then these wired and / or wireless technologies are included within the definition of transmission media.

[0064] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0065] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0066] The names used for the above-mentioned parameters are not limiting in any way. Furthermore, the formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure. The various information elements may be identified by any suitable names, and the various names assigned to these various information elements are not limiting in any way.

[0067] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0068] Any reference to an element using a designation such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must precede the second element in some way.

[0069] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Further, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0070] In this disclosure, where articles have been added due to translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0071] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0072] 10...analysis device, 11...receiving unit, 12...usage history database (storage unit), 13...extraction unit, 15...classification unit, 16...aggregation unit, 17...output unit, 20...user terminal (terminal device).

Claims

1. An analysis device that analyzes an input sentence input to a terminal device capable of executing a function corresponding to an input sentence of a user, comprising: a storage unit that associates the input sentence with information for distinguishing a user and stores the input sentence; an extraction unit that extracts the input sentences stored in the storage unit for each of the corresponding functions on a user-by-user basis; a classification unit that classifies the input sentences into intra-user similar groups for each function on a user-by-user basis such that the input sentences extracted by the extraction unit form intra-user similar groups constituted by input sentences that are similar to each other; an aggregating unit that aggregates the intra-user similar groups that are similar to each other between users in units of functions so that the intra-user similar groups form an inter-user similar group constituted by the intra-user similar groups that are similar to each other; and an output unit that outputs a result of the aggregation by the aggregation unit.

2. The analysis device according to claim 1 , wherein the aggregating unit calculates information including a number of the intra-user similar groups that constitute the inter-user similar group as the aggregation result.

3. The analysis device according to claim 1 , wherein the extraction unit extracts input sentences corresponding to functions that have been executed more frequently than a set reference within a set period.

4. The analysis device according to claim 3 , wherein the criterion is the number of days each of the functions has been performed.

5. the storage unit stores user attribute information associated with the input sentence, The analysis device according to claim 1 , wherein the aggregating unit aggregates the intra-user similar groups, which are similar to each other among users having at least a portion of the same attribute information, in units of functions.

Images