WO2016203805A1 - Dispositif, système, procédé et programme de traitement d'informations - Google Patents

Dispositif, système, procédé et programme de traitement d'informations Download PDF

Info

Publication number
WO2016203805A1
WO2016203805A1 PCT/JP2016/060208 JP2016060208W WO2016203805A1 WO 2016203805 A1 WO2016203805 A1 WO 2016203805A1 JP 2016060208 W JP2016060208 W JP 2016060208W WO 2016203805 A1 WO2016203805 A1 WO 2016203805A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
candidate
reply
information processing
Prior art date
Application number
PCT/JP2016/060208
Other languages
English (en)
Japanese (ja)
Inventor
高橋　慧
Original Assignee
ソニー株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ソニー株式会社 filed Critical ソニー株式会社
Publication of WO2016203805A1 publication Critical patent/WO2016203805A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • the present disclosure relates to an information processing apparatus, an information processing system, an information processing method, and a program.
  • an automatic reply technique has been developed that automatically replies to a received message or automatically generates reply candidates.
  • Patent Document 1 discloses a technique for supporting labor saving of mail input by a server that acquires and analyzes mail transmitted by a user.
  • the present disclosure proposes a new and improved information processing apparatus, information processing system, information processing method, and program that can personalize reply candidates more appropriately.
  • the generation unit that generates the second candidate information based on the first candidate information for output corresponding to the input information and the user information that is the information related to the first user, and the generation And an output control unit that performs control to output the second candidate information generated by the unit.
  • a server and a terminal device are provided, the server generates first candidate information for output corresponding to input information, and the terminal device is generated by the server. Based on the first candidate information and user information that is information about the first user, a generation unit that generates second candidate information, and a control that outputs the second candidate information generated by the generation unit There is provided an information processing system having an output control unit for performing.
  • An information processing method includes controlling the output of the second candidate information that has been performed by a processor.
  • the computer generates the second candidate information based on the first candidate information for output corresponding to the input information and the user information that is information related to the first user.
  • an output control unit that performs control to output the second candidate information generated by the generation unit are provided.
  • FIGS. 1 and 2 An overview of an information processing system according to an embodiment of the present disclosure will be described with reference to FIGS. 1 and 2.
  • FIG. 1 is an explanatory diagram for explaining an overview of a user terminal according to the present embodiment.
  • the user terminal 100 is a wristband type touch panel.
  • the user terminal 100 communicates with a mail server etc. by itself or via a smart phone etc., and receives a message.
  • the user terminal 100 displays a received message “Tell me if you arrived?
  • the received message is information based on contents input by another user (second user) different from the user (first user).
  • the received message refers to a message transmitted to the user from another user (more specifically, another device other than the user device 100 used by the user).
  • the communication path may be via a network such as LTE, or may be direct such as infrared communication.
  • the received message may be a message input to the user apparatus 100 by another user.
  • reply candidates are automatically generated by a server that acquires and analyzes mail transmitted by the user.
  • reply candidates are generated based only on the content of the received message, and no reply candidates are generated based on other information.
  • the information processing system according to the present embodiment has been created with the above circumstances in mind.
  • the information processing system according to the present embodiment shares the generation process of reply candidates between the user terminal and the server.
  • FIG. 2 is an explanatory diagram for explaining an overview of the information processing system according to the present embodiment.
  • the information processing system 1 includes a user terminal 100 and a reply candidate generation server 200.
  • the user terminal 100 is a terminal possessed by the user, and the reply candidate generation server 200 exists on the cloud.
  • the information processing system 1 acquires a received message from the mail server 300, generates a reply candidate, and outputs the generated reply candidate to the user.
  • the reply candidate generation server 200 includes a message analysis engine 201 and a reply pattern DB 202.
  • the message analysis engine 201 has a function of analyzing the content of the received message and generating a reply candidate by referring to the reply pattern DB 202.
  • the reply pattern DB 202 has a function of storing a general reply pattern corresponding to the content of the received message.
  • the message analysis engine 201 generates a general (for example, standard) reply candidate for the received message. For example, if the received message is “coming tomorrow?”, The message analysis engine 201 generates reply candidates “go” and “cannot go”. Such a general reply candidate is also referred to as a general reply candidate.
  • the reply candidate generation server 200 transmits the generated general-purpose reply candidate to the user terminal 100.
  • the user terminal 100 includes a reply candidate personalization engine 101 and a user information DB 102.
  • the user information DB 102 has a function of storing user information that is information about the user.
  • the reply candidate personalization engine 101 has a function of generating a reply candidate personalized by the user from the general reply candidates with reference to the user information DB 102. For example, if the general-purpose reply candidates are “go” and “cannot go”, the reply candidate personalization engine 101 generates reply candidates “I will go!” And “Stop!”. Such a personalized reply candidate is also referred to as a personalized reply candidate.
  • the user terminal 100 outputs the generated personalized reply candidate to the user.
  • the user selects a message to be actually replied from the personalized reply candidates (that is, the reply is permitted). Then, the personalized reply candidate selected by the user is returned as a reply message to another user who is the transmission source of the received message.
  • the general reply candidate generation process is performed in the reply candidate generation server 200, and the personalized reply candidate generation process is performed in the user terminal 100.
  • the user terminal 100 may not have software for generating a reply candidate and data of a reply pattern or may reduce it. As a result, the load and frequency of updates are reduced, and the risk of outflow of automatic reply technology is also reduced. Further, by such sharing, the reply candidate generation server 200 does not need to accumulate personal information such as a user's reply history, and can reduce the burden on service operation.
  • FIG. 1 illustrates an example in which the reply candidate generation server 200 acquires a received message directly from the mail server 300
  • the present technology is not limited to such an example.
  • the reply candidate generation server 200 may acquire a received message via the user terminal 100 and return the general reply candidate to the user terminal 100.
  • This technology supports character input performed by a user on a terminal device.
  • the present technology is particularly useful in a terminal device in which character input is impossible or character input is possible but a touch keyboard for inputting characters one by one cannot be used or is troublesome.
  • Examples of such a terminal device include a wearable device having a screen such as a glasses-type device in addition to the wristband device shown in FIG.
  • a smartphone, a tablet, a game machine, a TV, a projection display, and the like can be given.
  • it is also useful for a system that reads out a message by voice, such as a headphone or a speaker type device. It is also useful for in-vehicle devices that output messages by voice or screen during driving.
  • a reply to a message from another person by e-mail or chat can be considered.
  • a scene where a reply to an article is made on a Web page a scene where a comment on a photograph or a real world image is posted other than a document, and the like are also conceivable.
  • the present technology may be implemented in combination with an object recognition engine for extracting information from the image.
  • the first candidate information corresponds to a general-purpose reply candidate according to the present embodiment.
  • the second candidate information corresponds to a personalized reply candidate.
  • the input information corresponds to a received message.
  • FIG. 3 is a block diagram illustrating an example of a logical configuration of the user terminal 100 according to the present embodiment.
  • the user terminal 100 includes a communication unit 110, an output unit 120, an input unit 130, a storage unit 140, and a processing unit 150.
  • the communication unit 110 is a communication module for transmitting and receiving data to and from other devices by wire / wireless.
  • the communication unit 110 is connected to a local area network (LAN), a telephone line, or the like, and communicates with the reply candidate generation server 200 directly or via another communication node.
  • LAN local area network
  • telephone line or the like
  • Output unit 120 The output unit 120 outputs information by video, image, sound, vibration or the like.
  • Input unit 130 receives user input. As shown in FIG. 1, the output unit 120 and the input unit 130 may be integrally formed as a touch panel.
  • Storage unit 140 temporarily or permanently stores a program for operating the user terminal 100 and various data.
  • the storage unit 140 can function as the user information DB 102 illustrated in FIG.
  • Processing unit 150 provides various functions of the user terminal 100. As illustrated in FIG. 3, the processing unit 150 includes an acquisition unit 151, a learning unit 152, a generation unit 153, an output control unit 154, and a notification unit 155. The processing unit 150 may further include other components other than these components. That is, the processing unit 150 can perform operations other than the operations of these components. The functions of the acquisition unit 151, the learning unit 152, the generation unit 153, the output control unit 154, and the notification unit 155 will be described in detail later.
  • the processing unit 150 can function as the reply candidate personalization engine 101 shown in FIG. Next, the software configuration will be described with reference to FIG.
  • FIG. 4 is a diagram illustrating an example of a configuration of software installed in the user terminal 100 according to the present embodiment.
  • an OS Operating System
  • a messaging application 104 can be installed in the user terminal 100.
  • a character input application 105 can be installed in the user terminal 100.
  • the OS 103 provides file access, drawing, network communication, inter-application communication, and the like.
  • the messaging application 104 provides a service for sending and receiving messages between users.
  • the character input application 105 receives character input from the user.
  • the character input application 105 includes an automatic reply module 106, a voice input module 107, and a touch input module 108.
  • the automatic reply module 106 automatically generates reply candidates for the message received by the messaging application 104.
  • the automatic reply module 106 corresponds to the reply candidate personalization engine 101 shown in FIG.
  • the voice input module 107 realizes character input by voice.
  • the touch input module 108 realizes character input by touching the touch panel.
  • FIG. 5 is a block diagram illustrating an example of a logical configuration of the reply candidate generation server 200 according to the present embodiment. As illustrated in FIG. 5, the reply candidate generation server 200 includes a communication unit 210, a storage unit 220, and a processing unit 230.
  • the communication unit 210 is a communication module for transmitting and receiving data to and from other devices by wire / wireless.
  • the communication unit 210 is connected to a local area network (LAN) or a telephone line, and communicates with the user terminal 100 and the mail server 300 directly or via another communication node.
  • LAN local area network
  • Storage unit 220 The storage unit 220 temporarily or permanently stores a program for operating the reply candidate generation server 200 and various data.
  • the storage unit 220 can function as the reply pattern DB 202 illustrated in FIG.
  • Processing unit 230 provides various functions of the processing unit 230. As illustrated in FIG. 5, the processing unit 230 includes a learning unit 231, a generation unit 232, and a communication control unit 233. Note that the processing unit 230 may further include other components other than these components. That is, the processing unit 230 can perform operations other than the operations of these components. The functions of the learning unit 231, the generation unit 232, and the communication control unit 233 will be described in detail later.
  • the processing unit 230 can function as the message analysis engine 201 shown in FIG.
  • the configuration example of the reply candidate generation server 200 has been described above. Next, the technical features of the information processing system 1 according to the present embodiment will be described with reference to FIGS.
  • Reply candidate generation server 200 (for example, generating unit 232) generates a general-purpose reply candidate.
  • the general reply candidate is generated according to the analysis result of the received message.
  • the received message may include text information, image information, audio information, and the like.
  • the general-purpose reply candidate can also include text information, symbol information, pictographic information, stamp information, image information, audio information, and the like.
  • the text information is a concept including the text itself or text data (for example, a signal). The same applies to image information, audio information, and the like.
  • the reply candidate generation server 200 generates a general reply candidate using modality analysis and main part extraction using a language analyzer. These techniques are techniques for extracting the main questionable part of the message from the grammatical knowledge of the language of the received sentence. As a result, the user can effectively use the automatic reply function immediately after starting to use the system. Such a feature is particularly advantageous in wearable devices that do not have direct character input means.
  • the general-purpose reply candidate may include a plurality of expressions such as affirmation and denial, and may include a wild card in part so as to include a derivative expression such as a polite expression and a colloquial expression.
  • the reply candidate generation server 200 receives the received message from the mail server 300, and transmits the generated general reply candidate and the received message to the user terminal 100.
  • the user terminal 100 generates a personalized reply candidate.
  • the personalized reply candidate is a candidate for information to be notified (that is, returned) to the notification source of the received message (that is, another user (second user) of the message transmission source: hereinafter also referred to as a partner).
  • the personalized reply candidate may also include text information, symbol information, pictographic information, stamp information, image information, audio information, and the like.
  • the user terminal 100 acquires a general reply candidate for output corresponding to the received message (that is, output to the user by the output unit 120).
  • the user terminal 100 acquires a general reply candidate and a received message from the reply candidate generation server 200 in response to a timer, push notification, user instruction, or the like.
  • the user terminal 100 (for example, the generation unit 153) generates a personalized reply candidate based on the general reply candidate and the user information. For example, based on user information (for example, a user's reply message history), the user terminal 100 changes the general reply candidate to a sentence / spoken expression or adds a sentence end expression.
  • the user terminal 100 may generate personalized reply candidates further based on real-time user information. For example, the user terminal 100 sets the reply content in accordance with the behavior at that time based on the information indicating the user's behavior and the like acquired in real time.
  • the user terminal 100 performs control to output the generated personalized reply candidate.
  • the user terminal 100 causes the output unit 120 to output personalized reply candidates.
  • the user terminal 100 may output (for example, transmit) the personalized reply candidate to another device (for example, a display device or a wearable device). In this case, whether or not the personalized reply candidate is actually output (for example, displayed) to the user is determined by another device.
  • a plurality of personalized reply candidates may be generated, and the user terminal 100 can output a plurality of personalized reply candidates.
  • the user selects a message to be actually replied from the output personalized reply candidates (that is, the reply is permitted).
  • the user selects one personalized reply candidate from among them.
  • part or all of the personalized reply candidates may be corrected by the user.
  • the user terminal 100 (for example, the notification unit 155) notifies the other party of the personalized reply candidate selected to be notified by the user.
  • the user terminal 100 transmits the selected personalized reply candidate as a reply message to the reply candidate generation server 200, and the reply candidate generation server 200 (for example, the communication control unit 233) transfers the received reply message to the other party. To do. Thereby, a reply message is replied to the other party.
  • the user device 100 may transmit a reply message to the partner terminal (for example, the user device 100) without going through the reply candidate generation server 200, or directly using, for example, infrared communication or the like. It may be transmitted through a simple communication path.
  • the user device 100 may output personalized reply candidates to the partner.
  • User information may be stored in the storage unit 140, or may be acquired in real time when a personalized reply candidate is generated. Hereinafter, an example of user information will be described.
  • the user information may include information on messages transmitted / received by the user.
  • Message transmission history itself history of received messages and reply messages
  • Contents entered in full text ⁇ Edited contents from fixed sentences / existing sentences
  • IME input keyboard input, touch input, voice input
  • Recipients who send and receive messages ⁇ History of deleted / saved messages by users ⁇ History of sending and receiving messages
  • Elapsed time since receiving message (generated at the other terminal) (For example, if the elapsed time exceeds a predetermined value, a personalized reply candidate including an apology is generated. .)
  • the user information may include information relating to the user's human relationship as shown below.
  • Phone book data ⁇ Family relations ⁇ Friendships and relationships with colleagues in SNS ⁇ Game name, name, and role of RPG game (Recovery / Attack) ⁇ Whether the person who is exchanging messages is a human being or whether it is a company-to-person (customer) relationship
  • the user information may include information related to an application used by the user as shown in the following example.
  • ⁇ Browser browsing history ⁇ Frequently photographed ⁇ Frequently used and installed applications
  • Voice input information can be estimated from voice tone
  • the user information may include information on the user activity shown as an example below.
  • ⁇ History of location information rough area, school, university, company, theme park, restaurant, event
  • Biological information reflaxation and tension can be estimated from the pulse
  • Life patterns (9: 00-18: 00 are companies, etc.)
  • Schedule information ⁇ Sports such as running, history of action information such as movement
  • the user information may include user attribute information shown as an example below. ⁇ Birthplace, place of residence, nationality ⁇ Gender, age ⁇ Current occupation, affiliation ⁇ Hobbies (games, idols, etc.)
  • the user information may include information relating to other devices used by the user, which will be exemplified below.
  • Information on wearable devices such as smartwatches that are linked (for example, based on the biometric information accumulated in the smartwatch, there is a personalized reply candidate “I'm still running” for the received message “I ’m running?” Generated.)
  • Smart home information for example, a personalized reply candidate for the received message “Is milk still?” Is generated based on the refrigerator inventory information.
  • a personalized reply candidate “Wait a minute can't take your hands off” for the received message “Will you pick me up now?” Is generated.
  • -Information on cars-Data such as driving, stopping, driving on highways, driving on general roads-Car position-Passenger information
  • the user terminal 100 (for example, the generation unit 153) generates a personalized reply candidate by changing the text information of the general reply candidate based on the user information.
  • the generation unit 153 generates a personalized reply candidate by changing the text information of the general reply candidate based on the user information.
  • the user terminal 100 may generate a personalized reply candidate by changing the text representation of the general reply candidate based on the user information.
  • the user terminal 100 changes the expression of the general reply candidate based on words frequently used by the user, style, human relations, the current state of the user, and the like.
  • the user terminal 100 can generate a reply candidate as if it was input by the user, and an unnatural impression can be avoided.
  • An example of personalization of expression is shown below.
  • the user terminal 100 may generate a personalized reply candidate by adding information such as text or an image to the general reply candidate text.
  • information to be added include a sentence, a signature, a pictograph, a stamp, a photograph, and a moving image.
  • the user terminal 100 may generate a personalized reply candidate by omitting a part of the general reply candidate text. For example, an abbreviation becomes a personalized reply candidate.
  • the user terminal 100 may generate a personalized reply candidate by changing the ending of the text of the general reply candidate. For example, the user terminal 100 changes the ending to “Dayo” “Dane” “Daze” “!” “ ⁇ ” “ ⁇ ” or the like according to the relationship between the user and the other party. Thereby, the user terminal 100 can generate personalized reply candidates including a complicated expression, a revised expression, an emphasized expression, and the like.
  • the user terminal 100 may generate a personalized reply candidate by changing the text style of the general-purpose reply candidate text.
  • the user terminal 100 may change the style to a polite expression / spoken expression or the like. Thereby, the user terminal 100 can generate a personalized reply candidate including a simple expression or a revised expression.
  • the user terminal 100 generates a personalized reply candidate by changing a part or all of the general reply candidate text to a different text having the same or similar meaning. Also good.
  • the user terminal 100 may generate a personalized reply candidate by selecting one expression from variations of expressions having the same meaning such as “OK”, “OK”, and “OK”.
  • the reply candidate generation server 200 generates general reply candidates such as “I will go”, “Go ⁇ yo ⁇ ”, “I ’m sorry, it ’s impossible”, “I ’m sorry, I ’m busy”, “It ’s not good”, “I ca n’t go”. .
  • the user terminal 100 receives these general reply candidates together with the received message. Based on the user information, for example, the user terminal 100 outputs a personalized reply candidate “go!” To the user as the first candidate based on the fact that there are many endings “Ze!” For the same party, for example. To do. Further, the user terminal 100 outputs a personalized reply candidate “I'm sorry, it seems impossible” to the user as the first candidate based on the fact that there are many polite expressions with respect to another partner.
  • a stamp or a pictograph may be adopted as a reply message.
  • the reply candidate generation server 200 identifies a group of stamps or pictograms having the same or similar meaning with respect to reply candidates that frequently appear and can be expressed by stamps or pictograms such as “OK” or “Thank you”.
  • the identification information may be generated as a general reply candidate.
  • the user terminal 100 replaces the identification information with a stamp or a pictograph based on the user information, and outputs it as a personalized reply candidate.
  • the reply candidate generation server 200 generates a group name with a stamp “STAMP_PATTERN_OK” as a general-purpose reply candidate.
  • the user terminal 100 outputs a stamp belonging to the group “STAMP_PATTERN_OK”, which is frequently used by the user, to the user as a first candidate.
  • the user terminal 100 may generate personalization reply candidates by changing nouns included in the general reply candidate text based on user information. For example, the user terminal 100 changes a general noun included in the general-purpose reply candidate to the partner's nickname, secret word, buzzword, or the like. As a result, the user terminal 100 can generate a reply candidate as if it was input by the user, and an unnatural impression can be avoided.
  • the user terminal 100 may personalize the reply content. Specifically, the user terminal 100 may generate a personalized reply candidate that includes content corresponding to the content of the received message. For example, when the received message is “What are you doing now?” And when user information indicating that the user is currently running is acquired, “Running” is generated as a personalized reply candidate. For example, when the received message is “Is it a free time?”, When user information indicating a schedule of being in a meeting is acquired, “I am currently in a meeting” is generated as a personalized reply candidate.
  • the user terminal 100 may give variations to the personalized reply candidates. Thereby, it is prevented that the same reply message is sent back to the same person repeatedly.
  • the user terminal 100 may generate personalization reply candidates by diverting expressions included in the received message, for example.
  • a personalized reply candidate having the same style as the partner's style is generated.
  • a reply using a feminine expression similar to that of the other woman for example, heavy use of “lovely” in English is used even though the user is a man. , It may cause discomfort.
  • the user terminal 100 learns a change pattern for changing from a general reply candidate to a personalized reply candidate.
  • the user terminal 100 analyzes the content of the message input by the user, and extracts the utterance of the expression method such as which expression to use among endings, styles, and expression variations having the same meaning that the user often uses Then, it learns as a change pattern. For example, the user terminal 100 extracts a habit of expression method at the timing when the user performs a message transmission operation. For example, the user terminal 100 determines whether or not a phrase input by the user matches a pattern registered in advance, and extracts the matched pattern as a bag. Alternatively, the user terminal 100 may extract a ending pattern that appears characteristically using a morphological analyzer.
  • the user terminal 100 may register sentence ending expression patterns such as “ ⁇ susune” and “ ⁇ dayo” in advance, and extract the matched pattern as a bag.
  • the user terminal 100 may extract a new sentence end expression using a morphological analyzer or the like.
  • the user terminal 100 may register, for example, greeting patterns in advance and perform matching, or extract a new greeting expression using a morphological analyzer or the like.
  • the user terminal 100 or matching registered in advance such as "Chiwassu" "Hey hey” as a pattern similar to the "Hello", or to extract the unknown phrase in the beginning of a sentence as a new greeting representation To do.
  • the user terminal 100 may store dialect vocabulary dictionaries and detect dialects frequently used by the user, related vocabulary, and expression habits. In addition, regarding personalization of nouns, the user terminal 100 extracts what nickname a particular person is called, a role in a family or organization, etc. based on the content of a message transmitted and received by the user. Also good.
  • the user terminal 100 stores the extracted expression method trap in association with user information such as the partner with whom the message is exchanged and the user's behavior at the time of message input. Thereby, the user terminal 100 can generate a personalized reply candidate whose expression is changed in accordance with user information such as who the other party is and whether the user terminal is in a close relationship.
  • the change pattern learning may be performed in the user terminal 100 or may be performed in the reply candidate generation server 200 (for example, the learning unit 231).
  • information indicating the learning result of the change pattern is stored in the storage unit 140 of the user terminal 100 and is not stored in the reply candidate generation server 200.
  • the learning result of the change pattern may also be captured as user information.
  • the user terminal 100 may mix or switch multiple languages according to the reply partner. For example, for a partner who mainly communicates in Hindi and sometimes in English, the user terminal 100 uses English for writing to the SNS (for example, comments on articles posted by the partner), Vietnamese is used for communication. In countries where voice messages are common, the user terminal 100 may display a button that returns a voice message when replying to a complicated mail. Further, personalization corresponding to the ending expression in Japanese can be realized by selecting a term, selecting an auxiliary verb (for example, changing “want” to “would like to”), and the like.
  • role sharing is performed between the user terminal 100 and the reply candidate generation server 200, but the present technology is not limited to such an example.
  • a reply candidate may be generated only in one of them. That is, the general reply candidate may be adopted as a reply message as it is, or the personalized reply candidate may be generated without being based on the general reply candidate.
  • personalized reply candidates may be generated when the user terminal 100 is fixedly used by a single user or when an individual to be shared can be identified.
  • the function for generating personalized reply candidates is turned off for in-store demonstration machines and rental machines used by an unspecified number of people. Even when it is fixedly used by one user, the same applies when it is detected that the user is used by a different user. The same applies to cases where a different usage situation is detected.
  • a personalized reply candidate is generated without being based on the general reply candidate
  • the general reply candidate Or a personalized reply candidate without being based on the general reply candidate.
  • the user terminal 100 may generate a personalized reply candidate without being based on the learning result. For example, if the user sets a rule that a formal reply is better for a business email from a business partner, the learning result is not reflected and the personalized reply candidate of the formal content Is generated.
  • the user terminal 100 may generate personalized reply candidates based on simple user information created in advance. . For example, the user terminal 100 generates a personalized reply candidate using expressions, endings, greeting patterns, etc. that are often used by people who use " ⁇ tsusune", even if the end of " ⁇ tsusune" is extracted even once. To do.
  • FIG. 6 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • Reference numeral 400 indicates an example of a display screen displayed by the user terminal 100.
  • Reference numeral 401 indicates that “Mr. AAA” is a message transmission / reception partner (chat partner).
  • Reference numeral 402 indicates a history of transmitted and received messages.
  • Reference numeral 403 indicates an example of a personalized reply candidate. For example, when the user selects “eating!”, “Eating!” Is returned to the partner as a reply message.
  • FIG. 7 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • Reference numeral 410 indicates an example of a display screen displayed by the user terminal 100.
  • Reference numeral 411 indicates that “Mr. AAA” is a message transmission / reception partner.
  • Reference numeral 412 indicates a history of transmitted and received messages.
  • a reference numeral 413 indicates an example of a personalized reply candidate.
  • Reference numeral 414 indicates a button for displaying different personalized reply candidates. When the user presses the button, personalized reply candidates with different expressions such as “eat!” And “eat” can be displayed.
  • Reference numeral 415 also indicates a button for displaying different personalized reply candidates. When the user presses the button, for example personalized reply candidate of the different meanings of such as "Hello" may be displayed.
  • FIG. 8 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • Reference numerals 420, 425, and 426 indicate examples of display screens displayed by the user terminal 100.
  • Reference numeral 421 indicates that “Mr. AAA” is a message transmission / reception partner.
  • Reference numeral 422 indicates a history of transmitted and received messages.
  • Reference numeral 423 indicates a tab for selecting a change pattern used for generating a personalized reply candidate.
  • Reference numeral 424 indicates an example of a personalized reply candidate. For example, in the code
  • FIG. 9 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • Reference numeral 430 indicates an example of a display screen displayed by the user terminal 100.
  • Reference numeral 431 indicates that “Mr. AAA” is a message transmission / reception partner.
  • Reference numeral 432 indicates a history of transmitted and received messages.
  • Reference numeral 433 indicates an input field of IME (Input Method Editor).
  • Reference numeral 434 represents an example of a personalized reply candidate. For example, when the user selects “Eat!”, “Eat!” Is input in the input field 433.
  • Reference numeral 435 represents a character input key.
  • this technique can coexist with IME.
  • FIG. 10 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • the user terminal 100 is an in-vehicle device having a voice reading function using a speaker 441.
  • the in-vehicle device 100 may communicate with the reply candidate generation server 200 directly or indirectly via a smartphone or the like. Further, personalized reply candidate generation processing or the like may be performed in a smartphone or the like, and only input / output may be performed in the in-vehicle device 100.
  • the in-vehicle device 100 reads a received message, reads a personalized reply candidate, and transmits a reply message in response to a user operation on the button 442.
  • the in-vehicle device 100 is “A message from AAA.” Did you have lunch? Read “”. Subsequently, the in-vehicle device 100 reads “Reply“ I ate it when I press the button ”. When the user presses the button 442, the in-vehicle device 100 returns “I ate it”.
  • FIG. 11 is an explanatory diagram for explaining an example of a UI provided by the user terminal 100 according to the present embodiment.
  • the user terminal 100 is a headphone having a voice reading function using a speaker 451.
  • the headphone 100 may communicate with the reply candidate generation server 200 directly or indirectly via a smartphone or the like. Further, personalized reply candidate generation processing or the like may be performed on a smartphone or the like, and only input / output may be performed on the headphones 100.
  • the headphone 100 reads out the received message, reads out the personalized reply candidate, and transmits a reply message in response to a user operation on the button 452.
  • the headphones 100 are “A new message from AAA.” Did you eat lunch? Read “”. Subsequently, the headphone 100 reads out “Reply“ I ate it when I press the button ”. When the user presses the button 452, the headphone 100 returns “I ate it”.
  • FIG. 12 is a flowchart illustrating an example of a flow of learning processing executed in the user terminal 100 according to the present embodiment.
  • the user terminal 100 generates a message (step S102). For example, the user terminal 100 generates text with a text editor, transmits with a mail application, or generates a reply message based on touch input to the touch panel or voice input information.
  • the user terminal 100 acquires user information (step S104). For example, the user terminal 100 acquires user information based on a detection result by a built-in sensor, an analysis result of a Web page accessed by the user, and a message transmission partner.
  • the user terminal 100 learns a change pattern (step S106). For example, the user terminal 100 analyzes the content of the generated message, and extracts a habit of an expression method such as which expression to use among endings, styles, and expression variations having the same meaning that the user often uses. And learn as a change pattern. This step may be performed in the reply candidate generation server 200.
  • the user terminal 100 memorize
  • the user terminal 100 stores the learned change pattern in association with the acquired user information. Thereby, the process ends.
  • FIG. 13 is a sequence diagram showing an example of the flow of automatic reply processing executed in the information processing system 1 according to the present embodiment. As shown in FIG. 13, the user terminal 100 and the reply candidate generation server 200 are involved in this sequence.
  • the reply candidate generation server 200 receives a message from the mail server 300 (step S202), and generates a general reply candidate based on the received message (step S204). Next, the reply candidate generation server 200 transmits the received message and the generated general reply candidate to the user terminal 100 (step S206).
  • the user terminal 100 acquires user information (step S208), and generates a personalized reply candidate using the learned change pattern based on the user information and the received general-purpose reply candidate (step S210).
  • the user terminal 100 outputs the received message and the personalized reply candidate to the user (step S212), and acquires the user operation for selecting the personalized reply candidate (step S214).
  • the user terminal 100 transmits the personalized reply candidate selected by the user to the reply candidate generation server 200 as a reply message (step S216). Thereafter, a reply message is returned by the reply candidate generation server 200. Thereby, the process ends.
  • FIG. 14 is a block diagram illustrating an example of a hardware configuration of the information processing apparatus according to the present embodiment.
  • the information processing apparatus 900 illustrated in FIG. 14 can implement, for example, the user terminal 100 or the reply candidate generation server 200 illustrated in FIGS. 3 and 5, respectively.
  • Information processing by the user terminal 100 or the reply candidate generation server 200 according to the present embodiment is realized by cooperation of software and hardware described below.
  • the information processing apparatus 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, and a host bus 904a.
  • the information processing apparatus 900 includes a bridge 904, an external bus 904b, an interface 905, an input device 906, an output device 907, a storage device 908, a drive 909, a connection port 911, and a communication device 913.
  • the information processing apparatus 900 may include a processing circuit such as a DSP or an ASIC in place of or in addition to the CPU 901.
  • the CPU 901 functions as an arithmetic processing unit and a control unit, and controls the overall operation in the information processing apparatus 900 according to various programs. Further, the CPU 901 may be a microprocessor.
  • the ROM 902 stores programs used by the CPU 901, calculation parameters, and the like.
  • the RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like.
  • the CPU 901 can form, for example, the processing unit 150 shown in FIG. 3 or the processing unit 230 shown in FIG.
  • the CPU 901, ROM 902, and RAM 903 are connected to each other by a host bus 904a including a CPU bus.
  • the host bus 904 a is connected to an external bus 904 b such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 904.
  • an external bus 904 b such as a PCI (Peripheral Component Interconnect / Interface) bus
  • PCI Peripheral Component Interconnect / Interface
  • the host bus 904a, the bridge 904, and the external bus 904b do not necessarily have to be configured separately, and these functions may be mounted on one bus.
  • the input device 906 is realized by a device in which information is input by the user, such as a mouse, a keyboard, a touch panel, a button, a microphone, a switch, and a lever.
  • the input device 906 may be, for example, a remote control device using infrared rays or other radio waves, or may be an external connection device such as a mobile phone or a PDA that supports the operation of the information processing device 900.
  • the input device 906 may include, for example, an input control circuit that generates an input signal based on information input by the user using the above-described input means and outputs the input signal to the CPU 901.
  • a user of the information processing apparatus 900 can input various data and instruct a processing operation to the information processing apparatus 900 by operating the input device 906.
  • the input device 906 may be formed by a sensor that senses information about the user.
  • the input device 906 includes various sensors such as an image sensor (for example, a camera), a depth sensor (for example, a stereo camera), an acceleration sensor, a gyro sensor, a geomagnetic sensor, an optical sensor, a sound sensor, a distance sensor, and a force sensor. Can be included.
  • the input device 906 includes information related to the information processing device 900 state, such as the posture and movement speed of the information processing device 900, and information related to the surrounding environment of the information processing device 900, such as brightness and noise around the information processing device 900. May be obtained.
  • the input device 906 may also include a GPS sensor that receives GPS signals and measures the latitude, longitude, and altitude of the device.
  • the input device 906 can form, for example, the input unit 130 shown in FIG. In the present embodiment, the input device 906 acquires user information, for example.
  • the output device 907 is formed of a device that can notify the user of the acquired information visually or audibly.
  • Examples of such devices include CRT display devices, liquid crystal display devices, plasma display devices, EL display devices, display devices such as laser projectors, LED projectors and lamps, audio output devices such as speakers and headphones, printer devices, and the like.
  • the output device 907 outputs results obtained by various processes performed by the information processing device 900.
  • the display device visually displays results obtained by various processes performed by the information processing device 900 in various formats such as text, images, tables, and graphs.
  • the audio output device converts an audio signal composed of reproduced audio data, acoustic data, and the like into an analog signal and outputs it aurally.
  • the display device and the audio output device can form, for example, the output unit 120 shown in FIG.
  • the storage device 908 is a data storage device formed as an example of a storage unit of the information processing device 900.
  • the storage apparatus 908 is realized by, for example, a magnetic storage device such as an HDD, a semiconductor storage device, an optical storage device, a magneto-optical storage device, or the like.
  • the storage device 908 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like.
  • the storage device 908 stores programs executed by the CPU 901, various data, various data acquired from the outside, and the like.
  • the storage device 908 can form, for example, the storage unit 140 shown in FIG. 3 or the storage unit 220 shown in FIG.
  • the drive 909 is a storage medium reader / writer, and is built in or externally attached to the information processing apparatus 900.
  • the drive 909 reads information recorded on a removable storage medium such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and outputs the information to the RAM 903.
  • the drive 909 can also write information to a removable storage medium.
  • connection port 911 is an interface connected to an external device, and is a connection port with an external device capable of transmitting data by USB (Universal Serial Bus), for example.
  • USB Universal Serial Bus
  • the communication device 913 is a communication interface formed by a communication device or the like for connecting to the network 920, for example.
  • the communication device 913 is, for example, a communication card for wired or wireless LAN (Local Area Network), LTE (Long Term Evolution), Bluetooth (registered trademark), or WUSB (Wireless USB).
  • the communication device 913 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), a modem for various communication, or the like.
  • the communication device 913 can transmit and receive signals and the like according to a predetermined protocol such as TCP / IP, for example, with the Internet and other communication devices.
  • the communication device 913 may form, for example, the communication unit 110 illustrated in FIG. 3 or the communication unit 210 illustrated in FIG.
  • the network 920 is a wired or wireless transmission path for information transmitted from a device connected to the network 920.
  • the network 920 may include a public line network such as the Internet, a telephone line network, and a satellite communication network, various LANs including the Ethernet (registered trademark), a wide area network (WAN), and the like.
  • the network 920 may include a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network).
  • IP-VPN Internet Protocol-Virtual Private Network
  • each of the above components may be realized using a general-purpose member, or may be realized by hardware specialized for the function of each component. Therefore, it is possible to change the hardware configuration to be used as appropriate according to the technical level at the time of carrying out this embodiment.
  • a computer program for realizing each function of the information processing apparatus 900 according to the present embodiment as described above can be produced and mounted on a PC or the like.
  • a computer-readable recording medium storing such a computer program can be provided.
  • the recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, or the like.
  • the above computer program may be distributed via a network, for example, without using a recording medium.
  • a general reply candidate for output corresponding to the received message is acquired, a personalized reply candidate is generated based on the user information and the general reply candidate, and the generated personalized reply candidate is output.
  • the general reply candidate generation function and the personalized reply candidate generation function are shared by the user terminal 100 and the reply candidate generation server 200, so that the reply candidates can be personalized more appropriately.
  • this point will be described in detail.
  • a general reply candidate is generated in the reply candidate generation server 200. From this, it is possible to reduce the resource consumption of the CPU, memory, storage, etc. of the user terminal 100, so the types of terminals that can be used as the user terminal 100 are increased, the terminals are downsized, the battery life is extended, Realization of lower prices is expected. Further, since advanced processing is performed in the reply candidate generation server 200, the risk of outflow of automatic reply technology by reverse engineering is reduced. Furthermore, the software on the reply candidate generation server 200 side can be updated at an arbitrary timing.
  • the personalized reply candidate is generated in the user terminal 100. Accordingly, the reply candidate generation server 200 does not need to store user information for personalization, and does not need to identify a user when receiving access from the user terminal 100. Accordingly, there is no need for account generation for user authentication, authentication processing, and the like, so that user labor is reduced. Furthermore, since the reply candidate generation server 200 may return a general-purpose response to the input uniformly, parallelization of processing becomes easy.
  • the user terminal is provided with a secure storage on the premise that personal information is stored, and data can be cleared at the user's will.
  • various management costs such as ensuring security, performing maintenance, and providing an opt-out method may additionally occur.
  • the additional management cost is not generated.
  • this technology is a technology that supports character input. For this reason, cases where the present technology can be applied are not limited to messaging applications, but include various cases where characters can be input such as a browser or a game. Therefore, the function as the processing unit 150 described above may be incorporated in a character input module itself such as a touch input or voice input module. In that case, learning and personalization services for personalization are also provided in character input scenes other than messaging applications.
  • processing described with reference to the flowcharts and sequence diagrams in this specification may not necessarily be executed in the order shown. Some processing steps may be performed in parallel. Further, additional processing steps may be employed, and some processing steps may be omitted.
  • a generating unit that generates second candidate information based on first candidate information for output corresponding to input information and user information that is information about the first user;
  • An output control unit that performs control to output the second candidate information generated by the generation unit;
  • An information processing apparatus comprising: (2) The first candidate information and the second candidate information include text information, The information processing apparatus according to (1), wherein the generation unit generates the second candidate information by changing text information of the first candidate information based on the user information.
  • the generation unit adds a text or an image to the text of the first candidate information.
  • the information processing apparatus further includes a storage unit that stores information indicating a learning result of a change pattern for changing the user information and the first candidate information to the second candidate information.
  • the information processing apparatus according to any one of (8) to (8).
  • the second candidate information is a candidate for information to be notified to the second user.
  • the information processing apparatus further including a notification unit that notifies the second user of the second candidate information selected to be notified by the first user. .
  • the output control unit outputs a plurality of the second candidate information, The information processing apparatus according to (14), wherein the notification unit notifies one second candidate information selected by a user from among the plurality of second candidate information.
  • the user information includes information relating to messages sent and received by the user, information relating to user relationships, information relating to applications used by the user, information relating to user activities, user attribute information, and information relating to other devices used by the user.
  • the information processing apparatus according to any one of (1) to (15), including at least one.
  • a server and a terminal device The server generates first candidate information for output corresponding to the input information;
  • the terminal device Based on the first candidate information generated by the server and user information that is information about the first user, a generation unit that generates second candidate information, and the second generated by the generation unit
  • An information processing system having an output control unit that performs control to output candidate information.

Abstract

L'invention vise à fournir un dispositif, système, et procédé de traitement d'informations, ainsi qu'un programme, qui sont aptes à personnaliser de manière plus appropriée une réponse candidate. L'invention concerne un dispositif de traitement d'informations, comprenant : une unité de génération qui génère des secondes informations candidates, sur la base de premières informations candidates pour une sortie qui correspond à des informations entrées et des informations d'utilisateur qui sont des informations se rapportant à un premier utilisateur; et une unité de commande de sortie qui réalise une commande consistant à faire sortir les secondes informations candidates qui sont générées par l'unité de génération.
PCT/JP2016/060208 2015-06-15 2016-03-29 Dispositif, système, procédé et programme de traitement d'informations WO2016203805A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2015-120185 2015-06-15
JP2015120185 2015-06-15

Publications (1)

Publication Number Publication Date
WO2016203805A1 true WO2016203805A1 (fr) 2016-12-22

Family

ID=57545221

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/060208 WO2016203805A1 (fr) 2015-06-15 2016-03-29 Dispositif, système, procédé et programme de traitement d'informations

Country Status (1)

Country Link
WO (1) WO2016203805A1 (fr)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018135841A1 (fr) 2017-01-17 2018-07-26 Samsung Electronics Co., Ltd. Procédé de génération de message et dispositif électronique vestimentaire pour sa prise en charge
JP2018197986A (ja) * 2017-05-24 2018-12-13 東京瓦斯株式会社 端末装置、情報伝達方法、および、プログラム
CN109814730A (zh) * 2017-11-20 2019-05-28 北京搜狗科技发展有限公司 输入方法和装置、用于输入的装置
WO2019163224A1 (fr) * 2018-02-23 2019-08-29 ソニー株式会社 Dispositif de traitement d'informations, procédé de traitement d'informations et programme
WO2019172087A1 (fr) * 2018-03-08 2019-09-12 ソニー株式会社 Appareil de traitement d'informations, dispositif terminal, procédé de traitement d'informations et programme
JPWO2019116488A1 (ja) * 2017-12-14 2020-12-17 Ｌｉｎｅ株式会社 情報処理方法、情報処理装置、プログラム、及び情報処理端末
WO2021199727A1 (fr) * 2020-04-02 2021-10-07 Ｎｅｃソリューションイノベータ株式会社 Dispositif de commande d'affichage de contribution, procédé de commande d'affichage de contribution et programme

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012194775A (ja) * 2011-03-16 2012-10-11 Fujitsu Ltd 情報処理装置の制御方法、制御プログラム及び情報処理装置
JP2014134903A (ja) * 2013-01-08 2014-07-24 Biglobe Inc 送受信システム、送受信装置、及び送受信方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012194775A (ja) * 2011-03-16 2012-10-11 Fujitsu Ltd 情報処理装置の制御方法、制御プログラム及び情報処理装置
JP2014134903A (ja) * 2013-01-08 2014-07-24 Biglobe Inc 送受信システム、送受信装置、及び送受信方法

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10812418B2 (en) 2017-01-17 2020-10-20 Samsung Electronics Co., Ltd. Message generation method and wearable electronic device for supporting the same
WO2018135841A1 (fr) 2017-01-17 2018-07-26 Samsung Electronics Co., Ltd. Procédé de génération de message et dispositif électronique vestimentaire pour sa prise en charge
EP3542498A4 (fr) * 2017-01-17 2019-09-25 Samsung Electronics Co., Ltd. Procédé de génération de message et dispositif électronique vestimentaire pour sa prise en charge
CN110199503A (zh) * 2017-01-17 2019-09-03 三星电子株式会社 消息生成方法及用于支持该方法的可穿戴的电子设备
JP2018197986A (ja) * 2017-05-24 2018-12-13 東京瓦斯株式会社 端末装置、情報伝達方法、および、プログラム
CN109814730B (zh) * 2017-11-20 2023-09-12 北京搜狗科技发展有限公司 输入方法和装置、用于输入的装置
CN109814730A (zh) * 2017-11-20 2019-05-28 北京搜狗科技发展有限公司 输入方法和装置、用于输入的装置
JPWO2019116488A1 (ja) * 2017-12-14 2020-12-17 Ｌｉｎｅ株式会社 情報処理方法、情報処理装置、プログラム、及び情報処理端末
JP7072583B2 (ja) 2017-12-14 2022-05-20 Ｌｉｎｅ株式会社 情報処理方法、情報処理装置、プログラム、及び情報処理端末
US11270386B2 (en) 2018-02-23 2022-03-08 Sony Corporation Information processing device, information processing method, and program
WO2019163224A1 (fr) * 2018-02-23 2019-08-29 ソニー株式会社 Dispositif de traitement d'informations, procédé de traitement d'informations et programme
WO2019172087A1 (fr) * 2018-03-08 2019-09-12 ソニー株式会社 Appareil de traitement d'informations, dispositif terminal, procédé de traitement d'informations et programme
US11330408B2 (en) 2018-03-08 2022-05-10 Sony Corporation Information processing apparatus, terminal device, and information processing method
CN111788566A (zh) * 2018-03-08 2020-10-16 索尼公司 信息处理设备、终端装置、信息处理方法和程序
JPWO2021199727A1 (fr) * 2020-04-02 2021-10-07
WO2021199727A1 (fr) * 2020-04-02 2021-10-07 Ｎｅｃソリューションイノベータ株式会社 Dispositif de commande d'affichage de contribution, procédé de commande d'affichage de contribution et programme
JP7376185B2 (ja) 2020-04-02 2023-11-08 Ｎｅｃソリューションイノベータ株式会社 投稿の表示制御装置、投稿の表示制御方法、およびプログラム

Similar Documents

Publication Publication Date Title
WO2016203805A1 (fr) Dispositif, système, procédé et programme de traitement d'informations
US11036469B2 (en) Parsing electronic conversations for presentation in an alternative interface
US10986046B2 (en) Apparatus and method for generating summary of conversation storing
US11687720B2 (en) Named entity recognition visual context and caption data
RU2637874C2 (ru) Генерирование диалоговых рекомендаций для чатовых информационных систем
CN107609092B (zh) 智能应答方法和装置
US20150324065A1 (en) System and Method to Automatically Aggregate and Extract Key Concepts Within a Conversation by Semantically Identifying Key Topics
KR100695392B1 (ko) 단문 메시지를 멀티미디어 메시지로 변환 및 전송하는방법과 이를 수행하는 문자 이미지 변환서버
US20170249934A1 (en) Electronic device and method for operating the same
WO2013143252A1 (fr) Procédé et système pour susciter des mots candidats d'entrée sur la base d'un scénario de contexte
Lin et al. Text-messaging cultures of college girls in Hong Kong: SMS as resources for achieving intimacy and gift-exchange with multiple functions
WO2020177592A1 (fr) Procédé et dispositif de réponse à une question de peinture, système de réponse à une question de peinture, et support d'informations lisible
CN114303132A (zh) 在虚拟个人助手中使用唤醒词进行上下文关联和个性化的方法和系统
KR20160012965A (ko) 텍스트를 편집하는 방법 및 이를 지원하는 전자장치
JP2016006607A (ja) 対話型通信システム、端末装置およびプログラム
US20190364395A1 (en) Electronic device and method for processing message data of the electronic device
KR100627853B1 (ko) 단문 메시지를 멀티미디어 메시지로 변환하고 전송하는방법 및 문자 이미지 변환서버
Zhu A symbolism study of expression in text-based communication
CN111538998A (zh) 文本定密方法和装置、电子设备及计算机可读存储介质
CN109725798B (zh) 智能角色的切换方法及相关装置
CN114465975B (zh) 一种内容推送方法、装置、存储介质和芯片系统
Chan et al. Making telecommunications services accessible to people with severe communication disabilities
Joshi et al. Assistive Android Application for hearing impaired people using Sign Language
US20230236555A1 (en) Event-Based Reasoning for Assistant Systems
US20210021548A1 (en) Text messaging electronic device and server computer for registering context

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16811280

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16811280

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP