Recommendation device, recommendation method, program, and recording medium

Abstract

To provide a recommendation apparatus configured to recommend a sentence which expresses what a person feels and which is effective to another person.SOLUTION: A recommendation apparatus 10 includes: a qualification information acquisition unit 13 which acquires qualification information of another user, on the basis of identification information of the other user; a fixed phrase information acquisition unit 14 which acquires fixed phrase information (information formed by associating a fixed phrase, qualification information, and a degree of influence, for each fixed phrase on a feeling expression sentence) in accordance with the qualification information of the other user; a selection unit 15 which selects at least one fixed phrase from multiple fixed phrases on the basis of the degree of influence; and a recommendation unit 18 which recommends one user to use the fixed phrase as a feeling expression sentence.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a recommendation device, a recommendation method, a program, and a recording medium.

Background Art

[0002] In human-to-human conversation, it is important to convey one's feelings to the other person. For example, Patent Document 1 reports a technique for discriminating a user's feelings based on the magnitude of the user's grip strength and transmitting the discriminated feelings to other users.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, Patent Document 1 unilaterally conveys one's own feelings using a CG model without considering the other person. Therefore, there is a problem that one's own feelings are not sufficiently conveyed to the other person.

[0005] Therefore, an object of the present invention is to provide a recommendation device, a recommendation method, a program, and a recording medium that can recommend a sentence expressing one's own feelings and effective for the other person.

Means for Solving the Problems

[0006] To achieve the above object, the recommendation device of the present invention includes a qualification information acquisition unit, a stereotyped sentence information acquisition unit, a selection unit, and a recommendation unit, the qualification information acquisition unit acquires the qualification information of the other user based on the identification information of the other user, the qualification information is information indicating qualifications, The fixed phrase information acquisition unit acquires fixed phrase information corresponding to the qualification information of the other user, The fixed phrase information is information that associates the fixed phrase, the qualification information, and the influence degree for each fixed phrase related to the mood expression sentence, The influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the fixed phrase, The selection unit selects at least one of the plurality of fixed phrases based on the influence degree, The recommendation unit is a device that recommends to one user to use the fixed phrase as the mood expression sentence.

[0007] The recommendation method of the present invention includes a qualification information acquisition step, a fixed phrase information acquisition step, a selection step, and a recommendation step, In the qualification information acquisition step, based on the identification information of the other user, the qualification information of the other user is acquired, The qualification information is information indicating a qualification, In the fixed phrase information acquisition step, fixed phrase information corresponding to the qualification information of the other user is acquired, The fixed phrase information is information that associates the fixed phrase, the qualification information, and the influence degree for each fixed phrase related to the mood expression sentence, The influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the fixed phrase, In the selection step, at least one of the plurality of fixed phrases is selected based on the influence degree, The recommendation step is a method of recommending to one user to use the fixed phrase as the mood expression sentence.

Effects of the Invention

[0008] According to the present invention, it is possible to recommend to a user a sentence that expresses one's own mood and is effective for the other party.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0010] The recommendation device of the present invention includes, for example, further includes an untransmitted sentence acquisition unit, an extraction unit, and a recommended sentence generation unit, the untransmitted sentence acquisition unit acquires, by associating, from one user, an untransmitted mood expression sentence and identification information of the other user who is the transmission destination of the untransmitted mood expression sentence, the fixed phrase selected by the selection unit is an incomplete sentence that requests an input of at least one word, the extraction unit extracts at least one important word from the untransmitted sentence, the recommended sentence generation unit inputs the important word into the fixed phrase to generate a recommended sentence, The recommendation unit may be configured to recommend to the one user to use the generated recommended sentence as the mood expression sentence.

[0011] In the recommendation apparatus of the present invention, for example, The extraction unit includes a syntax analysis unit, a co-occurrence network formation unit, and a dictionary information acquisition unit, The syntax analysis unit performs syntax analysis on the untransmitted mood expression sentence, and extracts words that are nouns and words that are adjectives, The co-occurrence network formation unit forms a co-occurrence network having each of the extracted words as a vertex using each of the extracted words, The dictionary information acquisition unit acquires dictionary information in which words related to mood are recorded, The extraction unit may be configured to extract, as the important words, words that satisfy preset conditions based on the co-occurrence network and the dictionary information.

[0012] The recommendation apparatus of the present invention, for example, Further includes an evaluation information acquisition unit and an influence degree update unit, When the one user transmits a mood expression sentence to the other user using at least one of the fixed sentence and the recommended sentence recommended by the recommendation unit, The evaluation information acquisition unit acquires evaluation information indicating the evaluation of the other user with respect to the mood expression sentence, The influence degree update unit may be configured to update the influence degree using the evaluation information.

[0013] The recommendation apparatus of the present invention, for example, Further includes a recording unit, The recording unit records, as qualification information, by associating the identification information of the user with the qualification of the user, and For each fixed sentence related to the mood expression sentence, at least one of recording, as fixed sentence information, by associating the fixed sentence, the qualification information, and the influence degree, At least one of the qualification information acquisition unit and the fixed-form sentence information acquisition unit may be configured to acquire at least one of the recorded qualification information and the fixed-form sentence information.

[0014] In the recommendation device of the present invention, for example, The mood expression sentence may be a sentence expressing a positive mood.

[0015] In the recommendation device of the present invention, for example, The positive mood may be gratitude.

[0016] The recommendation method of the present invention, for example, Further includes an untransmitted sentence acquisition step, an extraction step, and a recommended sentence generation step. In the untransmitted sentence acquisition step, an untransmitted mood expression sentence is acquired in association with identification information of the other user who is the transmission destination of the untransmitted mood expression sentence from one user. The fixed-form sentence selected by the selection step is an incomplete sentence that requests input of at least one word. In the extraction step, at least one important word is extracted from the untransmitted sentence. In the recommended sentence generation step, the important word is input into the fixed-form sentence to generate a recommended sentence. The recommendation step may be configured to recommend to the one user to use the generated recommended sentence as the mood expression sentence.

[0017] In the recommendation method of the present invention, for example, The extraction step includes a syntax analysis step, a co-occurrence network formation step, and a dictionary information acquisition step. In the syntax analysis step, the untransmitted mood expression sentence is syntactically analyzed to extract words that are nouns and words that are adjectives. In the co-occurrence network formation step, a co-occurrence network having each of the extracted words as vertices is formed using each of the extracted words. The dictionary information acquisition step acquires dictionary information in which words related to feelings are recorded, The extraction step may be configured to extract, as the important words, words that satisfy preset conditions based on the co-occurrence network and the dictionary information.

[0018] The recommendation method of the present invention, for example, further includes an evaluation information acquisition step and an influence degree update step, When the one user transmits a feeling expression sentence to the other user using at least one of the set phrases and the recommended sentences recommended by the recommendation step, the evaluation information acquisition step acquires evaluation information indicating the evaluation of the other user with respect to the feeling expression sentence, The influence degree update step may be configured to update the influence degree using the evaluation information.

[0019] The recommendation method of the present invention, for example, further includes a recording step, the recording step records, as qualification information, associating the identification information of the user with the qualification of the user, and for each set phrase related to the feeling expression sentence, at least one of recording the set phrase, the qualification information, and the influence degree as set phrase information, At least one of the qualification information acquisition step and the set phrase information acquisition step may be configured to acquire at least one of the recorded qualification information and the set phrase information.

[0020] In the recommendation method of the present invention, for example, the feeling expression sentence may be a sentence expressing a positive feeling.

[0021] In the recommendation method of the present invention, for example, the positive feeling may be gratitude.

[0022] The program of the present invention is a program for causing a computer to execute each step of the method of the present invention as a procedure.

[0023] The recording medium of the present invention is a computer-readable recording medium recording the program of the present invention.

[0024] In the present invention, "mood" refers to a person's mental state, emotions, way of thinking, mood, etc., and should be interpreted in the broadest sense including positive moods and negative moods, and is not limited in any sense. Examples of the positive mood include gratitude, happiness, fun, joy, support, praise, respect, pride, excitement, peace, etc., and examples of the negative mood include sadness, loneliness, hardship, pain, ache, fear, apology, worry, sorrow, etc.

[0025] Next, embodiments of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiments. In the following drawings, the same parts are denoted by the same reference numerals. Also, unless otherwise specified, the descriptions of the respective embodiments can be mutually referred to, and the configurations of the respective embodiments can be combined unless otherwise specified.

[0026] [Embodiment 1] FIG. 1 is a block diagram showing a configuration example of a recommendation device 10 according to the present embodiment. As shown in FIG. 1, the device 10 includes, for example, a recording unit 11, an untransmitted sentence acquisition unit 12, a qualification information acquisition unit 13, a fixed sentence information acquisition unit 14, a selection unit 15, an extraction unit 16, a recommended sentence generation unit 17, a recommendation unit 18, an evaluation information acquisition unit 19, and an influence degree update unit 20. Note that the recording unit 11, the untransmitted sentence acquisition unit 12, the extraction unit 16, the recommended sentence generation unit 17, the evaluation information acquisition unit 19, and the influence degree update unit 20 are optional configurations and may not be included in the device 10. Further, the extraction unit 16 may include, for example, a syntax analysis unit 161, a co-occurrence network formation unit 162, and a dictionary information acquisition unit 163.

[0027] The device 10 may be, for example, one device including the above-described respective parts, or the respective parts may be devices connectable via a communication line network. Further, the device 10 can be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and a known network can be used. For example, it may be wired or wireless. Examples of the communication line network include an Internet line, WWW (World Wide Web), a telephone line, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (local 5G), and the like. Examples of the wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), local 5G, LPWA, and the like. The wireless communication may be in a form in which each device directly communicates (Ad Hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 10 may be incorporated into a server as a system, for example. Further, the device 10 may be, for example, a personal computer (PC, for example, a desktop type or a notebook type) installed with the program of the present invention, a smartphone, a tablet terminal, a wearable device (such as a smartwatch), or the like. Furthermore, the device 10 may be in a form such as cloud computing or edge computing, for example, in which at least one of the above-described respective parts is on a server and the other respective parts are on a terminal.

[0028] FIG. 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, a display device 106, a communication device 107, and the like. Each part of the device 10 is interconnected via the bus 103 by respective interfaces (I / F).

[0029] The central processing unit 101 is responsible for the overall control of the apparatus 10. In the apparatus 10, the central processing unit 101 executes, for example, the program of the present invention and other programs, and reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as a recording unit 11, an untransmitted sentence acquisition unit 12, a qualification information acquisition unit 13, a fixed sentence information acquisition unit 14, a selection unit 15, an extraction unit 16, a recommended sentence generation unit 17, a recommendation unit 18, an evaluation information acquisition unit 19, and an influence degree update unit 20.

[0030] The bus 103 can be connected to, for example, an external device. Examples of the external device include an external storage device (external database, etc.), a printer, an external input device, an external display device, an external imaging device, etc. The apparatus 10 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0031] The memory 102 includes, for example, a main memory (primary storage device). When the central processing unit 101 performs processing, for example, the memory 102 reads various operation programs such as the program of the present invention stored in the storage device 104 described later, and the central processing unit 101 receives data from the memory 102 and executes the program. The main memory is, for example, a RAM (random access memory). Further, the memory 102 may be, for example, a ROM (read-only memory).

[0032] The memory device 104 is, for example, also referred to as a so-called auxiliary storage device with respect to the main memory (primary storage device). As described above, an operation program including the program of the present invention is stored in the memory device 104. The memory device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited, and may be, for example, an internal type or an external type, and examples include an HD (hard disk), a CD-ROM, a CD-R, a CD-RW, an MO, a DVD, a flash memory, a memory card, and the like. The memory device 104 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD).

[0033] In the present apparatus 10, the memory 102 and the memory device 104 can also store various types of information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present apparatus 10, and information used when the present apparatus 10 executes processing. Note that at least some of the information may be stored in an external server other than the memory 102 and the memory device 104, for example, or may be distributed and stored in a plurality of terminals using blockchain technology or the like. Further, the memory 102 and the memory device 104 may store various types of information recorded by the recording unit 11, for example.

[0034] The present apparatus 10 may further include, for example, an input device 105 and a display device 106. The input device 105 is, for example, a touch panel, a keyboard, a mouse, or the like. Examples of the display device 106 include an LED display and a liquid crystal display.

[0035] The present apparatus 10 may further include, for example, a qualification information database 1, a standard sentence information database 2, and a dictionary information database 3 as shown in FIG. 1. The present apparatus 10 can be connected to the qualification information database 1, the standard sentence information database 2, and the dictionary information database 3 via the communication network, for example.

[0036] Next, an example of the recommendation method of the present embodiment will be described based on the flowchart of FIG. 3. The recommendation method of the present embodiment is implemented as follows, for example, using the recommendation device 10 of FIG. 1. Note that the recommendation method of the present embodiment is not limited to the use of the recommendation device 10 of FIG. 1. Also, the steps shown in parentheses in FIG. 3 are optional steps.

[0037] The recommendation method of the present embodiment may, for example, at least one of the following: recording, in advance by the recording unit 11, the identification information of the user and the qualifications of the user as qualification information in association with each other; and recording, for each fixed phrase related to the mood expression sentence, the fixed phrase, the qualification information, and the influence degree as fixed phrase information in association with each other (S11, recording step). The recording unit 11 may, for example, use a known technique (such as StrengthsFinder, etc.) for identifying the qualifications of the user, and record the qualifications identified by the technique in association with the identification information of the user. The recording unit 11 may, for example, store the dictionary information described later in the step (S11). Specific explanations of the qualification information, the fixed phrase information, and the dictionary information (hereinafter, also collectively referred to as qualification information, etc.) will be described later. The recording unit 11 may, for example, construct a database for storing the qualification information, etc. In the present invention, the database for storing the qualification information is referred to as the qualification information database 1, the database for storing the fixed phrase information is referred to as the fixed phrase information database 2, and the database for storing the dictionary information is referred to as the dictionary information database 3. Also, the recording unit 11 may, for example, record by storing the qualification information, etc. in an external database, or record by storing the qualification information, etc. in the memory 102 and the storage device 104.

[0038] First, for example, the unsent message acquisition unit 12 may acquire, from one user, an unsent mood expression message and identification information of the other user who is the recipient of the unsent mood expression message, in association with each other (S12, unsent message acquisition step). Hereinafter, the unsent mood expression message is also referred to as an unsent message. The mood expression message is, for example, a message expressing the mood of the one user towards the other user. The unsent message acquisition unit 12 may be acquired, for example, from an external device via the communication network.

[0039] Next, the aptitude information acquisition unit 13 acquires the aptitude information of the other user based on the identification information of the other user (S13, aptitude information acquisition step). The aptitude information is information indicating aptitude. The aptitude, in other words, is also referred to as, for example, nature, talent, ability, thinking, temperament, etc. Specifically, examples of the aptitude include sociability, cooperation, communication ability, positive temperament, competitiveness, strategicness, sense of responsibility, introspection, etc. The aptitude information acquisition unit 13 may acquire the aptitude information from the outside via the communication network, or may acquire the aptitude information recorded by the recording unit 11 (for example, the aptitude information stored in the aptitude information database 1, etc.).

[0040] Next, the fixed phrase information acquisition unit 14 acquires fixed phrase information corresponding to the qualification information of the other user (S14, fixed phrase information acquisition step). The fixed phrase information is information that associates the fixed phrase, the qualification information, and the influence degree for each fixed phrase related to the mood expression sentence. The influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the fixed phrase. Here, the fixed phrase may be an incomplete sentence that requests the input of at least one word, or may be a complete sentence. The incomplete sentence can become a complete sentence by inputting important words extracted by the extraction unit 16 described later or any word input by the user into the part that requests the input of the word. There may be two or more parts that request the input of the word. The complete sentence means a sentence that is established as a sentence, that is, a sentence whose meaning is understood without inputting a new word. The influence degree for each fixed phrase can be updated, for example, by the influence degree update unit 20 described later. The fixed phrase information acquisition unit 14 may acquire the fixed phrase information from the outside via the communication network, for example, or may acquire the fixed phrase information recorded by the recording unit 11 (for example, the fixed phrase information stored in the fixed phrase information database 2, etc.).

[0041] Next, the selection unit 15 selects at least one of the plurality of fixed phrases based on the influence degree (S15, selection step). The fixed phrase selected by the selection unit 15 may be the incomplete sentence or the complete sentence.

[0042] When the set phrase selected by the selection unit 15 is the incomplete sentence, for example, after the step (S15), at least one important word may be extracted from the unsent text by the extraction unit 16 (S16, extraction step). The extraction unit 16 may use a known algorithm such as TextRank, for example. Hereinafter, an example in which the extraction unit 16 includes a syntax analysis unit 161, a co-occurrence network formation unit 162, and a dictionary information acquisition unit 163 will be described for the specific processing of the step (S16). The syntax analysis unit 161 performs syntax analysis on the unsent emotional expression text and extracts words that are nouns and words that are adjectives (S161, syntax analysis step). Next, the co-occurrence network formation unit 162 forms a co-occurrence network having the extracted words as vertices using the extracted words (S162, co-occurrence network formation step). The co-occurrence network is, for example, a network showing the co-occurrence relationship of the words. Next, the dictionary information acquisition unit 163 acquires dictionary information in which words related to emotions are recorded (S163, dictionary information acquisition step). The dictionary information acquisition unit 163 may acquire the dictionary information from the outside via the communication line network, for example, or may acquire the dictionary information recorded by the recording unit 11 (for example, the dictionary information stored in the dictionary information database 3). As the dictionary information, for example, an existing dictionary such as the Japanese Emotional Expression Dictionary (URL: http: / / www.jnlp.org / SNOW / D18) can be used. Then, the extraction unit 16 extracts words that satisfy preset conditions as the important words based on the co-occurrence network and the dictionary information (S164, extraction step). The preset conditions are not particularly limited and can be arbitrarily set. Specifically, examples of the conditions include words with a high degree, words in the dictionary information, words with a score calculated by a preset formula higher than other words, and combinations of any two or more of these. The formula is not particularly limited.

[0043] Next, after the step (S16), for example, by the recommended sentence generation unit 17, the important words are input into the fixed sentence to generate a recommended sentence (S17, recommended sentence generation step). That is, it can be said that the recommended sentence is a fixed sentence that has become the complete sentence due to the input of the important words.

[0044] And when the steps (S16) to (S17) are not executed, the recommendation unit 18 recommends to the one user to use the fixed sentence as the mood expression sentence (S18, recommendation step), and ends (END). In this case, the recommendation unit 18 may recommend the fixed sentence that is the incomplete sentence to the one user, or may recommend the fixed sentence that is the complete sentence to the one user. On the other hand, when the steps (S16) to (S17) are executed, in the step (S18), the recommendation unit 18 recommends to the one user to use the generated recommended sentence as the mood expression sentence. In this case, the recommended sentence recommended to the one user is a complete sentence as described above. The recommendation unit 18 may recommend, for example, by displaying the fixed sentence on a display device (display device 106 or an external display device), or may recommend by transmitting the fixed sentence to the one user via the communication line network.

[0045] Hereinafter, after the step (S18), the process (steps (S19) to (S20)) when the one user transmits a mood expression sentence to the other user using at least one of the fixed sentence and the recommended sentence recommended by the recommendation unit 18 will be described. Note that the transmission may be performed, for example, by the present device 10 or by an external device.

[0046] First, after the step (S18), the evaluation information acquisition unit 19 acquires evaluation information indicating the evaluation of the other user for the mood expression sentence (S19, evaluation information acquisition step). The evaluation is, for example, an evaluation meaning whether the mood expression sentence can arouse a favorable impression, and may be a multi-stage evaluation. The evaluation information acquisition unit 19 may acquire the evaluation information from the outside via the communication line network, for example.

[0047] Next, after the step (S19), the influence degree update unit 20 updates the influence degree using the evaluation information (S20, influence degree update step), and then ends (END). Specifically, it will be described later.

[0048] According to the present embodiment, by considering the qualifications of the other user, it is possible to recommend to the one user an emotional expression text that is effective for the other user, in other words, an emotional expression text in which the emotion is easily conveyed to the other party. Thus, according to the present embodiment, it is possible to eliminate the anxiety of users (senders of emotional expression texts) such as "not knowing what words to send to the other party" and "not knowing whether the emotion sent by oneself has been conveyed to the other party". In addition, by generating the recommended text, it is not necessary for the one user to take trouble, so it becomes easier for the other user to send an emotional expression text (the recommended text).

[0049] [Embodiment 2] The present invention will be specifically described by taking a text expressing gratitude as an example of the emotional expression text.

[0050] An example of the recording unit 11 constructing the qualification information database 1, the fixed phrase information database 2, and the dictionary information database 3 will be described with reference to FIGS. 4 and 5. FIG. 4 is an example of the qualification information database 1, the fixed phrase information database 2, and the dictionary information database 3. In FIG. 4, the qualification information is linked with the user identification information (user name) of the user and the qualifications of the user. The recording unit 11 constructs the qualification information database 1, for example, by using a known technique (such as StrengthsFinder, etc.) to record the qualification information as described above and accumulating the qualification information.

[0051] The set phrase in the set phrase information in FIG. 4 is an incomplete sentence, and "***" is the part that requests the input of the word. Also, the higher the numerical value of the influence degree, the greater the mental influence. FIG. 5 shows an example of calculating the influence degree. First, although not shown, the monitor identifies its own qualifications by using a known technique such as a strengths finder using the terminal of the monitor (for example, a smartphone, etc.). Next, the monitor registers the qualifications in the input field of the questionnaire site using the terminal (labeled "1" in the figure). Next, the device (for example, this device 10) that operates the questionnaire site displays a question regarding the set phrase on the questionnaire site and presents the question to the monitor (labeled "2" in the figure). Specifically, the question is, for example, a question that can be answered as like or dislike, such as "Do you like the word ''?". The '' is, for example, the set phrase itself set in advance. Next, the monitor registers the answer to the question in the input field of the questionnaire site using the terminal of the monitor (labeled "3" in the figure). Next, the device calculates the influence degree by dividing the "number of monitors who answered that they like ''" by the "number of monitors who answered the question" among a plurality of monitors having the same qualifications. Then, the recording unit 11 associates the set phrase '', the qualifications, and the influence degree to record the set phrase information, and constructs the set phrase information database 2 by accumulating the set phrase information.

[0052] The dictionary information in FIG. 4 has words related to "thanks" associated with their readings (katakana). The recording unit 11 constructs the dictionary information database 3 by accumulating the dictionary information.

[0053] Fig. 6 shows an example of the processing of the extraction unit 16. An example of the unsent text acquired by the unsent text acquisition unit 11 is shown at the upper part of Fig. 6. The syntax analysis unit 161 performs syntax analysis on this unsent text, and as shown in the figure, extracts words representing nouns and words representing adjectives. The co-occurrence network formation unit 162 forms the co-occurrence network shown in Fig. 6 by the processing described later. Also, it is assumed that the dictionary information acquisition unit 163 has acquired the dictionary information shown in Fig. 4. The extraction unit 16 extracts, for example, the nouns "approval" and "earlier" that are close in distance to the word "thank you" which is a word in the dictionary information as candidates for the important words within the co-occurrence network. Then, the extraction unit 16 extracts, for example, the word with a high score calculated by the following formula (1) among the candidates as the important word. Note that the "weight" in the following formula (1) can be arbitrarily set, for example, 5, 10, 15, etc. In the case of this example, as shown in Fig. 6, since the score of "approval" is higher than the score of "earlier", the extraction unit 16 extracts "approval" as the important word. On the other hand, the extraction unit 16 may extract "approval" with the highest frequency of "4" as the important word even without using the following formula (1). Score = (number of occurrences) + (words in adjacent dictionary information) × (weight) ··· (1)

[0054] Fig. 7 shows an example of the processing by the co-occurrence network formation unit 162. First, as shown at the upper part of Fig. 7, the co-occurrence network formation unit 162 creates an adjacency matrix using the words representing nouns and the words representing adjectives extracted by the syntax analysis unit 161. Here, the adjacency matrix is a matrix in which each column and each row correspond to each vertex of the co-occurrence network, and the part where there is an edge becomes 1. Next, as shown in the middle part of Fig. 7, the co-occurrence network formation unit 162 updates the adjacency matrix by setting "1" for adjacent words. For the update of the adjacency matrix, for example, a known technique such as a 1-gram model can be used. Then, as shown in the lower part of Fig. 7, the co-occurrence network formation unit 162 forms the co-occurrence network based on the adjacency matrix.

[0055] FIG. 8 shows an example of the processing by the fixed phrase information acquisition unit 14, the selection unit 15, and the recommended sentence generation unit 17. The fixed phrase information acquisition unit 14 acquires fixed phrase information corresponding to the aptitude "sociability" of the other user "Suzuki". In this example, as shown in FIG. 8, it is assumed that the fixed phrase information regarding the same aptitude "sociability" as the aptitude "sociability" of "Suzuki" is acquired as the fixed phrase information. As shown in the figure, the fixed phrase information acquisition unit 14 may acquire a plurality of the fixed phrase information. The selection unit 15 selects the fixed phrase with the highest influence degree among the plurality of the fixed phrase information. As shown in FIG. 8, the recommended sentence generation unit 17 inserts the important word "approval" extracted by the processing shown in FIG. 6 into the "***" of the fixed phrase to generate a recommended sentence that is a complete sentence.

[0056] In this way, by the series of processes described in this embodiment, the unsent sentence shown in FIG. 6 can be converted into the recommended sentence shown in FIG. 8.

[0057] [Embodiment 3] A specific example of updating the influence degree will be described.

[0058] The other user inputs evaluation information indicating an evaluation of the received mood expression sentence, for example, using the terminal (such as a smartphone, etc.) of the other user. In other words, the evaluation means whether a favorable feeling can be held for the mood expression sentence. Specifically, for example, when the other user can have a favorable feeling for the mood expression sentence, the other user may tap a button indicating a favorable feeling such as "Like!" on the display of the terminal to evaluate. On the other hand, for example, when the other user cannot have a favorable feeling for the mood expression sentence, the other user does not have to tap the button indicating the favorable feeling, or may tap a button indicating an unfavorable feeling such as "BAD" to evaluate.

[0059] The evaluation information acquisition unit 19 acquires the evaluation information associated with the mood expression text. The evaluation information includes, for example, favorable evaluation information indicating that the user has a favorable impression of the mood expression text, and unfavorable evaluation information indicating that the user has an unfavorable impression of the mood expression text. When, for example, the button indicating the favorable impression is tapped, the evaluation information acquisition unit 19 acquires the favorable evaluation information as the evaluation information. On the other hand, when, for example, the button indicating the unfavorable impression is tapped, or when the button indicating the favorable impression is not tapped within a preset period after the other user receives the mood expression text, the evaluation information acquisition unit 19 acquires the unfavorable evaluation information as the evaluation information.

[0060] When, for example, the favorable evaluation information is acquired, the influence degree update unit 20 updates the influence degree by adding a preset weight to the influence degree. On the other hand, when, for example, the unfavorable evaluation information is acquired, the influence degree update unit 20 updates the influence degree by subtracting a preset weight from the influence degree. The weight is not particularly limited and can be arbitrarily set, for example, 0.03, 0.05, 1.0, etc. FIG. 9 shows an example of the update of the influence degree when the unfavorable evaluation information is acquired. In this case, as shown in the figure, the influence degree update unit 20 calculates a numerical value "0.17" by subtracting the weight "0.05" from the influence degree "0.23" of the fixed phrase corresponding to the sent mood expression text. Then, the influence degree update unit 20 updates the influence degree of the fixed phrase corresponding to the sent mood expression text from "0.23" to "0.17".

[0061] By updating the influence degree in this way, a fixed phrase more suitable for the qualities of the other user can be selected, and a more effective mood expression text can be recommended to the one user.

[0062] [Embodiment 4] The program of this embodiment is a program for causing a computer to execute each step of the method of the present invention as a procedure. In the present invention, "procedure" may be read as "process". Further, the program of this embodiment may be recorded on, for example, a computer-readable recording medium. The recording medium is not particularly limited, and examples thereof include a read-only memory (ROM), a hard disk (HD), and an optical disk.

[0063] As described above, the present invention has been described with reference to the embodiments. However, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0064] <Supplementary Note> Some or all of the above embodiments may be described as follows, but are not limited thereto. (Supplementary Note 1) Including a qualification information acquisition unit, a set phrase information acquisition unit, a selection unit, and a recommendation unit, The qualification information acquisition unit acquires the qualification information of the other user based on the identification information of the other user, The qualification information is information indicating a qualification, The set phrase information acquisition unit acquires set phrase information corresponding to the qualification information of the other user, The set phrase information is information associating the set phrase, the qualification information, and the influence degree for each set phrase related to the mood expression sentence, The influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the set phrase, The selection unit selects at least one of the plurality of set phrases based on the influence degree, The recommendation unit is a recommendation device that recommends using the set phrase as the mood expression sentence to one user. (Supplementary Note 2) Furthermore, including an untransmitted sentence acquisition unit, an extraction unit, and a recommended sentence generation unit, The non-transmitted text acquisition unit acquires, by associating, from one user, a non-transmitted sentiment expression text and identification information of the other user who is the destination of the non-transmitted sentiment expression text. The fixed sentence selected by the selection unit is an incomplete sentence that requests the input of at least one word. The extraction unit extracts at least one important word from the non-transmitted text. The recommended text generation unit inputs the important word into the fixed sentence to generate a recommended text. The recommendation unit recommends to the one user to use the generated recommended text as the sentiment expression text, the recommendation device according to Appendix 1. (Appendix 3) The extraction unit includes a syntax analysis unit, a co-occurrence network formation unit, and a dictionary information acquisition unit. The syntax analysis unit performs syntax analysis on the non-transmitted sentiment expression text and extracts words that are nouns and words that are adjectives. The co-occurrence network formation unit forms a co-occurrence network with the extracted words as vertices using each of the extracted words. The dictionary information acquisition unit acquires dictionary information in which words related to sentiment are recorded. The extraction unit extracts, as the important word, a word that satisfies a preset condition based on the co-occurrence network and the dictionary information, the recommendation device according to Appendix 2. (Appendix 4) Furthermore, it includes an evaluation information acquisition unit and an influence degree update unit. When the one user transmits a sentiment expression text to the other user using at least one of the fixed sentence and the recommended text recommended by the recommendation unit, The evaluation information acquisition unit acquires evaluation information indicating the evaluation of the other user for the sentiment expression text. The influence degree update unit updates the influence degree using the evaluation information, the recommendation device according to any one of Appendices 1 to 3. (Appendix 5) Furthermore, it includes a recording unit. The recording unit records, as qualification information, by associating the identification information of the user with the qualification of the user, and for each fixed expression related to the mood expression sentence, records at least one of the following: associating the fixed expression, the qualification information, and the influence degree as fixed expression information. At least one of the qualification information acquisition unit and the fixed expression information acquisition unit acquires at least one of the recorded qualification information and the fixed expression information. The recommendation device according to any one of Appendices 1 to 4. (Appendix 6) The mood expression sentence is a sentence expressing a positive mood. The recommendation device according to any one of Appendices 1 to 5. (Appendix 7) The positive mood is gratitude. The recommendation device according to any one of Appendices 1 to 6. (Appendix 8) Includes a qualification information acquisition process, a fixed expression information acquisition process, a selection process, and a recommendation process. In the qualification information acquisition process, based on the identification information of the other user, the qualification information of the other user is acquired. The qualification information is information indicating a qualification. In the fixed expression information acquisition process, fixed expression information corresponding to the qualification information of the other user is acquired. The fixed expression information is information that associates the fixed expression, the qualification information, and the influence degree for each fixed expression related to the mood expression sentence. The influence degree is an index indicating the degree of the mental influence received when a user having the qualification indicated by the qualification information receives the fixed expression. In the selection process, at least one fixed expression is selected from among a plurality of the fixed expressions based on the influence degree. In the recommendation process, the fixed expression is recommended to one user to be used as the mood expression sentence. A recommendation method. (Appendix 9) Furthermore, it includes an untransmitted sentence acquisition process, an extraction process, and a recommended sentence generation process. The untransmitted text acquisition step acquires, by associating an untransmitted sentiment expression text with identification information of the other user who is the destination of the untransmitted sentiment expression text, from one user, The fixed sentence selected by the selection step is an incomplete sentence that requests input of at least one word. The extraction step extracts at least one important word from the untransmitted text. The recommended text generation step generates a recommended text by inputting the important word into the fixed sentence. The recommendation step recommends to the one user to use the generated recommended text as the sentiment expression text, the recommendation method described in Supplementary Note 8. (Supplementary Note 10) The extraction step includes a syntactic analysis step, a co-occurrence network formation step, and a dictionary information acquisition step. The syntactic analysis step performs syntactic analysis on the untransmitted sentiment expression text and extracts words that are nouns and words that are adjectives. The co-occurrence network formation step forms a co-occurrence network having each of the extracted words as vertices, using each of the extracted words. The dictionary information acquisition step acquires dictionary information in which words related to sentiment are recorded. The extraction step extracts, as the important word, a word that satisfies a preset condition based on the co-occurrence network and the dictionary information, the recommendation method described in Supplementary Note 9. (Supplementary Note 11) Furthermore, it includes an evaluation information acquisition step and an influence degree update step. When the one user transmits a sentiment expression text to the other user using at least one of the fixed sentence and the recommended text recommended by the recommendation step, The evaluation information acquisition step acquires evaluation information indicating the evaluation of the other user with respect to the sentiment expression text. The influence degree update step updates the influence degree using the evaluation information, the recommendation method described in any one of Supplementary Notes 8 to 10. (Supplementary Note 12) Furthermore, it includes a recording step. The recording process records, as qualification information, by associating the identification information of the user with the qualification of the user, and executes at least one of: recording, for each set phrase related to the mood expression sentence, the set phrase, the qualification information, and the influence degree as set phrase information; At least one of the qualification information acquisition step and the set phrase information acquisition step acquires at least one of the recorded qualification information and the set phrase information by the recommendation method described in any one of Appendices 8 to 11. (Appendix 13) The mood expression sentence is a sentence expressing a positive mood, by the recommendation method described in any one of Appendices 8 to 12. (Appendix 14) The positive mood is gratitude, by the recommendation method described in any one of Appendices 8 to 13. (Appendix 15) A program for causing a computer to execute a procedure including a qualification information acquisition procedure, a set phrase information acquisition procedure, a selection procedure, and a recommendation procedure: The qualification information acquisition procedure acquires the qualification information of the other user based on the identification information of the other user, The qualification information is information indicating a qualification, The set phrase information acquisition procedure acquires set phrase information corresponding to the qualification information of the other user, The set phrase information is information in which, for each set phrase related to the mood expression sentence, the set phrase, the qualification information, and the influence degree are associated, The influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the set phrase, The selection procedure selects at least one of the plurality of set phrases based on the influence degree, The recommendation procedure recommends to one user to use the set phrase as the mood expression sentence. (Appendix 16) Furthermore, it includes an untransmitted sentence acquisition procedure, an extraction procedure, and a recommended sentence generation procedure, The unsent message acquisition procedure obtains, by associating with each other, an unsent sentiment expression message and identification information of the other user who is the destination of the unsent sentiment expression message, from one user. The fixed phrase selected by the selection procedure is an incomplete sentence that requests the input of at least one word. The extraction procedure extracts at least one important word from the unsent message. The recommended message generation procedure generates a recommended message by inputting the important word into the fixed phrase. The recommendation procedure recommends to the one user to use the generated recommended message as the sentiment expression message, the program described in Appendix 15. (Appendix 17) The extraction procedure includes a syntax analysis procedure, a co-occurrence network formation procedure, and a dictionary information acquisition procedure. The syntax analysis procedure performs syntax analysis on the unsent sentiment expression message and extracts words that are nouns and words that are adjectives. The co-occurrence network formation procedure forms a co-occurrence network having each of the extracted words as a vertex, using each of the extracted words. The dictionary information acquisition procedure acquires dictionary information in which words related to sentiment are recorded. The extraction procedure extracts, as the important word, a word that satisfies a preset condition based on the co-occurrence network and the dictionary information, the program described in Appendix 16. (Appendix 18) Furthermore, it includes an evaluation information acquisition procedure and an influence degree update procedure. When the one user transmits a sentiment expression message to the other user using at least one of the fixed phrase and the recommended message recommended by the recommendation procedure, The evaluation information acquisition procedure acquires evaluation information indicating the evaluation of the other user with respect to the sentiment expression message. The influence degree update procedure updates the influence degree using the evaluation information, the program described in any one of Appendices 15 to 17. (Appendix 19) Furthermore, it includes a recording procedure. The recording procedure includes recording, as qualification information, linking the identification information of the user and the qualifications of the user, and executing at least one of: for each fixed sentence related to the mood expression sentence, recording the fixed sentence, the qualification information, and the degree of influence as fixed sentence information by linking them. At least one of the qualification information acquisition procedure and the fixed sentence information acquisition procedure is a program described in any one of Appendices 15 to 18 that acquires at least one of the recorded qualification information and the fixed sentence information. (Appendix 20) The mood expression sentence is a sentence expressing a positive mood, and is a program described in any one of Appendices 15 to 19. (Appendix 21) The positive mood is gratitude, and is a program described in any one of Appendices 15 to 20. (Appendix 22) A computer-readable recording medium recording a program described in any one of Appendices 15 to 21.

Industrial Applicability

[0065] According to the present invention, it is possible to recommend a sentence that expresses one's own mood and is effective for the other party. Therefore, the present invention is useful, for example, when sending a mood such as gratitude in a sentence.

Explanation of Signs

[0066] 1 Qualification Information Database 2 Fixed Sentence Information Database 3 Dictionary Information Database 10 Recommendation Device 11 Recording Unit 12 Unsentence Acquisition Unit 13 Qualification Information Acquisition Unit 14 Fixed Sentence Information Acquisition Unit 15 Selection Unit 16 Extraction Unit 161 Syntax Analysis Unit 162 Co-occurrence Network Formation Unit 163 Dictionary Information Acquisition Unit 17 Recommendation Information Generation Unit 18 Recommendation Unit 19 Evaluation Information Acquisition Unit 20 Influence Degree Analysis Unit 101 Central Processing Unit 102 Memory 103 Bus 104 Storage Device 105 Input Device 106 Display Device 107 Communication Device

Claims

1. comprising an untransmitted text acquisition unit, a qualification information acquisition unit, a set phrase information acquisition unit, a selection unit, and a recommendation unit, the untransmitted text acquisition unit acquires, by associating, from one user, an untransmitted emotional expression text and identification information of another user who is the destination of the untransmitted emotional expression text, the qualification information acquisition unit acquires the qualification information of the other user based on the identification information of the other user, the qualification information is information indicating a qualification, the set phrase information acquisition unit acquires set phrase information corresponding to the qualification information of the other user, the set phrase information is information associating, for each set phrase related to an emotional expression text, the set phrase, the qualification information, and an influence degree, the influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the set phrase, the selection unit selects at least one of the plurality of set phrases based on the influence degree, the recommendation unit recommends to one user to use the set phrase as the emotional expression text, a recommendation device.

2. further comprising an extraction unit and a recommended text generation unit, the set phrase selected by the selection unit is an incomplete sentence that requests an input of at least one word, the extraction unit extracts at least one important word from the untransmitted emotional expression text, the recommended text generation unit inputs the important word into the set phrase to generate a recommended text, the recommendation unit recommends to the one user to use the generated recommended text as the emotional expression text, the recommendation device according to claim 1.

3. the extraction unit includes a syntax analysis unit, a co-occurrence network formation unit, and a dictionary information acquisition unit, the syntax analysis unit performs syntax analysis on the untransmitted emotional expression text to extract a word that is a noun and a word that is an adjective, the co-occurrence network formation unit forms a co-occurrence network having each of the extracted words as a vertex using each of the extracted words, the dictionary information acquisition unit acquires dictionary information in which words related to emotions are recorded, the extraction unit extracts, as the important word, a word that satisfies a preset condition based on the co-occurrence network and the dictionary information, the recommendation device according to claim 2.

4. further comprising an evaluation information acquisition unit and an influence degree update unit, When the one user transmits an emotional expression message to the other user by using at least one of the set phrases and the recommended sentences recommended by the recommendation unit, the evaluation information acquisition unit acquires evaluation information indicating the evaluation of the other user with respect to the emotional expression message, the influence degree update unit updates the influence degree by using the evaluation information, the recommendation device according to claim 2 or 3.

5. Furthermore, it includes a recording unit, the recording unit records, as qualification information, by associating the identification information of the user with the qualification of the user, the qualification information acquisition unit acquires the recorded qualification information, the recommendation device according to any one of claims 1 to 4.

6. Furthermore, it includes a recording unit, the recording unit records, as set phrase information, by associating each set phrase related to the emotional expression message with the qualification information and the influence degree for each set phrase, the set phrase information acquisition unit acquires the recorded set phrase information, the recommendation device according to any one of claims 1 to 5.

7. The emotional expression message is a message expressing a positive emotion, the recommendation device according to any one of claims 1 to 6.

8. The positive emotion is gratitude, the recommendation device according to claim 7.

9. It includes an untransmitted message acquisition step, a qualification information acquisition step, a set phrase information acquisition step, a selection step, and a recommendation step, the untransmitted message acquisition step acquires, by associating an untransmitted emotional expression message from one user with the identification information of the other user who is the transmission destination of the untransmitted emotional expression message, the qualification information acquisition step acquires the qualification information of the other user based on the identification information of the other user, the qualification information is information indicating a qualification, the set phrase information acquisition step acquires set phrase information corresponding to the qualification information of the other user, the set phrase information is information in which each set phrase related to the emotional expression message is associated with the qualification information and the influence degree, the influence degree is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the set phrase, the selection step selects at least one of the set phrases from among a plurality of the set phrases based on the influence degree, the recommendation step recommends to one user to use the set phrase as the emotional expression message, a recommendation method.

10. Furthermore, it includes an extraction step and a recommended sentence generation step, The set phrase selected by the selection step is an incomplete sentence that requests the input of at least one word. The extraction step extracts at least one important word from the unsent emotional expression text. The recommended text generation step inputs the important word into the set phrase to generate a recommended text. The recommendation step recommends to the one user to use the generated recommended text as the emotional expression text. The recommendation method according to claim 9.

11. A program for causing a computer to execute a procedure including an unsent text acquisition procedure, a qualification information acquisition procedure, a set phrase information acquisition procedure, a selection procedure, and a recommendation procedure: The unsent text acquisition procedure acquires, by associating, an unsent emotional expression text from one user and identification information of another user who is the destination of the unsent emotional expression text. The qualification information acquisition procedure acquires the qualification information of the other user based on the identification information of the other user. The qualification information is information indicating a qualification. The set phrase information acquisition procedure acquires set phrase information corresponding to the qualification information of the other user. The set phrase information is information that associates the set phrase, the qualification information, and the degree of influence for each set phrase related to the emotional expression text. The degree of influence is an index indicating the degree of mental influence received when a user having the qualification indicated by the qualification information receives the set phrase. The selection procedure selects at least one of the set phrases from among a plurality of the set phrases based on the degree of influence. The recommendation procedure recommends to one user to use the set phrase as the emotional expression text.

Images