WO2023057492A1 - Agent conversationnel en interface entre une machine et des utilisateurs - Google Patents
Agent conversationnel en interface entre une machine et des utilisateurs Download PDFInfo
- Publication number
- WO2023057492A1 WO2023057492A1 PCT/EP2022/077658 EP2022077658W WO2023057492A1 WO 2023057492 A1 WO2023057492 A1 WO 2023057492A1 EP 2022077658 W EP2022077658 W EP 2022077658W WO 2023057492 A1 WO2023057492 A1 WO 2023057492A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- message
- machine
- type
- terminal
- terminals
- Prior art date
Links
- 238000000034 method Methods 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000036651 mood Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 1
- 239000003795 chemical substances by application Substances 0.000 description 52
- 238000011022 operating instruction Methods 0.000 description 5
- 238000013475 authorization Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000001755 vocal effect Effects 0.000 description 3
- 102100028043 Fibroblast growth factor 3 Human genes 0.000 description 2
- 102100024061 Integrator complex subunit 1 Human genes 0.000 description 2
- 101710092857 Integrator complex subunit 1 Proteins 0.000 description 2
- 108050002021 Integrator complex subunit 2 Proteins 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000002826 coolant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/06—Message adaptation to terminal or network requirements
- H04L51/066—Format adaptation, e.g. format conversion or compression
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/18—Commands or executable codes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/212—Monitoring or handling of messages using filtering or selective blocking
Definitions
- the present invention relates to the field of instant messaging.
- a “chatroom” or “discussion room” is a virtual meeting place. Users have respective terminals for exchanging instant messages via a messaging server. In practice, these messages are exchanged by running an application installed in each user terminal. For example, a user can choose, according to the theme proposed or the interest of the moment, a subject of discussion in order to dialogue by keyboard or by voice messages, with several participants on this subject. The chatroom therefore typically offers a virtual meeting between several human users.
- an instant messaging discussion may relate to the operation of a machine. It may be desired, for example, to control the operation of the machine appropriately after consultation between several professionals.
- the present invention improves the situation.
- chatbot a computer conversational agent (for example of the type commonly called a “chatbot”) interfacing between at least one machine and user terminals running an instant messaging application.
- a first aspect of the invention relates to a method of communication between several devices including a machine and a plurality of user terminals, the method being implemented by a conversational computer agent as an interface between said several devices, the conversational computer agent being able to dialogue independently with the terminals and the machine, the terminals executing an instant messaging application in which the users participate in a discussion with the conversational computer agent by exchanging messages via their terminal.
- the method comprises at least:
- the present invention then makes it possible to enrich the experience of using the machine thanks to a conversational agent (or “chatbot” hereafter) which can dialogue:
- the conversational agent can use a knowledge base (of machine data, of data relating to previous user actions and comments, or other).
- the conversational computer agent upon receipt of a message of the first type from the machine:
- This content may relate to a type of operation in progress, or to states of the machine in a given operation, or others.
- the knowledge database can then include information specific to a professional sector of such a collaborative work environment.
- the messages transmitted by the conversational agent can include information on the machine (status, current operation, alerts, lack of raw material, history, etc.), or even professional tasks to be assigned to a party at least of the participants in the discussion.
- the method may include a consultation of the knowledge base to organize a sequential coordination of the professional tasks assigned to the participants, according to a current state of the machine and an identification of the participants in the discussion.
- the discussion can be scheduled in a collaborative setting, in an environment other than a professional work setting but with constraints specific to this other environment.
- the machine is a motor vehicle (or simply comprises parts of this vehicle)
- the safety of persons in the vehicle or around the vehicle involves constraints which can be formalized and integrated into the aforementioned knowledge base.
- constraints linked to the environment of use may not be attached to a specific machine.
- specific data communication rules for example personal user data
- the generation of a message of the second type intended for the machine may include:
- Such an embodiment makes it possible, for example, to coordinate requests from different users, or even to formulate, for example, an appropriate setting instruction for the machine according to a current state of the machine.
- the conversational computer agent can apply a filtering rule to avoid sending the message of the second type to the machine, at least as a function of data from a terminal sending the message from the first type.
- This data from the transmitting terminal may include, for example, a terminal identifier (an IMSI-type terminal number, or other) as belonging to a user authorized to send requests intended for the machine.
- a terminal identifier an IMSI-type terminal number, or other
- Such a request can be, for example, an operating instruction, or a request for an operating report or a history of settings, etc.
- the aforementioned datum of the transmitter terminal may comprise current geolocation data of the transmitter terminal and the filtering is applied if a distance between the transmitter terminal and the machine is greater than a threshold.
- the data item from the sender terminal may comprise current timestamp data item sent by the sender terminal with the message of the first type.
- the aforementioned filtering can be applied if the current timestamp is outside a predetermined range of daily (usual) times.
- this timestamp can be used to list in chronological order the various requests from the users of the terminals, in order to follow an appropriate sequence of operation of the machine. For example, if an instruction given to the machine contradicts an operation in progress, the timestamp is taken into account to determine: - if a change in operation is necessary (in the case of a recent timestamp), or
- the data from the sender terminal includes a score for detecting a predetermined mood, identified in the message of the first type, and the filtering is applied if this score is greater than a threshold.
- the conversational agent can be configured not to transmit, for example, a instructions from the user to the machine.
- the detection of the aforementioned predetermined mood can be enriched by a detection of voice components in said voice message (a higher pitch revealing typically anger, for example).
- the conversational computing agent can also apply a filtering rule to avoid sending a message of the second type to one of said plurality of terminals if this terminal is identified as belonging to a user. not authorized to receive message content sent by the machine.
- messages that can be filtered can be machine status messages, log messages or others.
- the conversational agent can be configured according to the type of content and for given authorizations, for example.
- the conversational computing agent can, in one embodiment, analyze a message received from a terminal and/or generate a message intended for a terminal, in natural language.
- the conversational computing agent can reciprocally analyze a message received from the machine and/or generate a message intended for the machine, in formal language.
- a message received from the machine which may include, for example, a machine status signal, determined from a measurement from at least one sensor that the machine includes, this message then being able to be interpreted in language formal
- a message received from the machine which may include, for example, a machine status signal, determined from a measurement from at least one sensor that the machine includes, this message then being able to be interpreted in language formal
- a computer program comprising instructions for implementing the method presented above, when this program is executed by a processor.
- a non-transitory, computer-readable recording medium on which such a program is recorded.
- a computer device comprising:
- such a DIS device may include:
- a second interface INT2 to be connected to user terminals TER via a virtual chat room CR (for example via a messaging server SER illustrated in Figure 1 commented on below), and a processing circuit comprising for example:
- processor PROC connected to the two interfaces INT1 and INT2, as well as to the memory MEM to read and execute the instructions of the aforementioned computer program.
- Such a device DIS material (hardware), can implement the software functionalities of a computer module such as the conversational agent intervening in the method within the meaning of the invention and bearing the reference CRB on the drawings shown below.
- FIG. 1 shows an example of the implementation context of a computer conversational agent according to one embodiment of the invention.
- FIG. 2 shows an example of steps of a method according to one embodiment of the invention.
- FIG. 3 shows an example of a device implementing a computer conversational agent according to one embodiment of the invention.
- chat room animated by an instant messaging application running on users' TER terminals, as messaging clients CC (for "chat client”), and
- CRB for "chatroom bridge” interfacing with the machine on the one hand, and the virtual chat room on the other hand.
- the chat room CR can be materialized by a messaging server SER to which the conversational agent CRB and the terminals TER are connected to exchange messages.
- the chat room CR and the conversational agent CRB are computer modules grouped together in the same server to which the terminals TER, on the one hand, and the machine MA, on the other hand, are connected.
- Each TER user terminal has a man-machine interface (screen/keyboard, loudspeaker/microphone, or others) for signaling received messages and/or for entering messages to be sent (these messages can be written, voice or other messages). Messages can thus be exchanged between CC users and also be shared with the conversational agent CRB.
- a man-machine interface screen/keyboard, loudspeaker/microphone, or others
- the conversational agent CRB can itself also dialogue with one or more of the users connected to the chat room.
- chatbots are computer conversational agents capable of dialoging with a single user usually.
- the conversational agent CRB is able to dialogue with several users, who can be recognized for example by a terminal identifier (IMSI for example) or an instant messaging client identifier, or even by voice. in the case of voice messages exchanged, or otherwise.
- IMSI terminal identifier
- voice voice messages exchanged, or otherwise.
- the design of such a human-machine interface is influenced by the competition on the Turing test and it is a question of giving the illusion that a computer program thinks through a meaningful dialogue with one or, here, several users.
- the chatbot is therefore usually intended for a dialogue between an IT agent and one (or here several) user(s), natural person(s).
- a chatbot can implement artificial intelligence and thus, as the dialogue with one or more users progresses, enrich its knowledge base to improve the quality of its responses over time.
- the conversational agent CRB is remarkable here in that it is able to dialogue:
- the conversational agent CRB can implement artificial intelligence to establish these interactions based on learning over time (possibly starting from predetermined initial rules). For example, data from a history of the states received from the machine, and/or from a history of user requests and/or exchanges between users can be assimilated by learning to constitute a knowledge base that the chatbot to interact with users and the machine. Typically, reactions received from the terminals following the reception of data from the machine can enrich the aforementioned knowledge base.
- This knowledge base may initially comprise pre-programmed data, specific to the machine and possibly to the context of its use. The conversational agent can then take into account the respective degrees of authorization of the users, and/or their competence and/or their experience, to weight its reactions to requests from these users. [0048] With reference to FIG. 2, the conversational agent CRB is therefore configured for:
- an LN natural language statement analyzer (French, English, or other) to interpret user requests (received at a prior step S1) and then determine, by referring to the database BC knowledge, relevance and/or consistency of these requests (depending, for example, on current operation of the machine, an operating history of the machine, or other), and thus prepare the appropriate research to perform near the machine,
- step S3 in formal language LF, expected by the machine
- step S4 these may be adjustment instructions CONS, requests for operating states of the machine, error report, or others
- this data not being able to respond to a specific request from a user: it may be for example alert messages ( abnormal operation, missing raw material, or others), then identify in the knowledge base relevant users to whom to transmit this data, as well as a context of current use and/or a history of similar use, or others,
- the MA machine shown in Figure 1 can be an industrial machine or more generally any piece of equipment (for example a domestic robot or other), capable of being supervised and/or controlled remotely, by sending messages computers. It can directly or indirectly (according to observations by a third party user) trace information, in particular on its current operation, following a request or on its own initiative (notably alerts).
- the machine may include one or more sensors capable of delivering (physical) parameter measurement signals in messages received by the conversational agent CRB.
- the machine can be, for example, any factory machine (a machine tool or other) and send the signals from its sensors en bloc to the conversational agent CRB.
- it may be a group of machines delivering each of the signals from its sensors to the conversational agent CRB, which is then configured to aggregate these different data and establish a summary for the participants in the discussion.
- an MA machine such as an automobile
- tire wear sensors independent of an on-board computer of the vehicle can also transmit information to the CRB agent on the state of wear of the tires.
- information can be transmitted to the driver on an upcoming deadline to fill the brake fluid and take the opportunity to change tires.
- machine thus designates both a single machine and several parts of the same machine communicating separately with the conversational agent, or even several distinct machines.
- the conversational agent is capable of interpreting the content of the messages that the machine returns (or that separate parts of the machine return) to obtain, for example, machine status data, or even information on the current operation of the machine, or others.
- the conversational agent CRB can also deduce from the messages received from the machine MA knowledge coming to enrich the aforementioned knowledge base, by storing this knowledge data in a memory (in a formalism of its own).
- the CRB agent can thus interpret the messages coming from the TER terminals, in natural language, and return corresponding knowledge when the subject of discussion of these messages is a request for information, for example.
- the CRB agent can, to respond to a request for information, return previously stored knowledge, or alternatively request the information from the machine MA and then return it to the terminals TER.
- the CRB agent can also transform a message received from the machine into knowledge and send it spontaneously to the participants in the chat room when necessary (case of an alert for example).
- the CRB agent can, by taking into account a specific set of rules, adopt a particular overall behavior with a chosen "personality" (for example, to show himself to be dominant, or expressive , analytical, sympathetic, or others).
- This specific set of rules can be chosen and configured by an authorized user/administrator.
- the CRB agent can implement a configurable rules engine. For example, the CRB agent can respond to participants' requests, depending on their "authorization" to intervene on the machine. Authorizations can be granted to users to be able to transmit instructions to the machine or simply to access certain information from the machine. In this case, the CRB agent can store a list of terminal identifiers (IMSI, IP address, or others) or users (login, pseudo or others) who are authorized to transmit requests or receive certain data of the machine, and otherwise filter these requests or data.
- IMSI terminal identifiers
- IP address IP address
- users login, pseudo or others
- the filtering on the instructions to be applied to the machine can be based on other criteria (alternatively or in combination).
- the CRB agent can also filter a request coming from a terminal, normally authorized, but whose current geolocation shows that the user is too far from the machine to be able to transmit an appropriate operating instruction.
- the CRB agent can also filter a request coming from a terminal, normally authorized, but whose timestamp does not correspond to a range of usual working hours (for example between 8 and 20 hours on weekdays). It can be suspected that such an instruction could have been sent to the machine in an emergency state which was not justified and/or in a thoughtless way.
- the CRB agent can also analyze an emotion in a message received from a user and can then filter its request (for example an operating instruction) if he detects in this message for example anger (an instruction transmitted for example in a state of annoyance, and possibly thoughtless) or fear (a hesitant and uncertain instruction for example ). Furthermore, if the message received from the user is a vocal message, the detection of this mood can be enriched by a detection of vocal components in this vocal message (for example an unusually high-pitched voice can reflect fear or possibly anger).
- the present invention thus provides security for the operation of the machine, as well as precision and speed of the response of the machine while facilitating the user experience thanks to the combination of natural language, artificial intelligence and the provision of all machine data.
- the user thus has an ease of interaction in order to check, or even repair, the machine more quickly.
- a conversational agent capable of dialoguing with a machine on the basis of knowledge specific to this machine has been described above.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP22798131.3A EP4413715A1 (fr) | 2021-10-06 | 2022-10-05 | Agent conversationnel en interface entre une machine et des utilisateurs |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FRFR2110582 | 2021-10-06 | ||
FR2110582A FR3127828A1 (fr) | 2021-10-06 | 2021-10-06 | Agent conversationnel en interface entre une machine et des utilisateurs |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023057492A1 true WO2023057492A1 (fr) | 2023-04-13 |
Family
ID=79171336
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/077658 WO2023057492A1 (fr) | 2021-10-06 | 2022-10-05 | Agent conversationnel en interface entre une machine et des utilisateurs |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP4413715A1 (fr) |
FR (1) | FR3127828A1 (fr) |
WO (1) | WO2023057492A1 (fr) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015109946A1 (fr) * | 2014-01-24 | 2015-07-30 | Tencent Technology (Shenzhen) Company Limited | Procédés et dispositifs de commande de machines |
US20160021038A1 (en) * | 2014-07-21 | 2016-01-21 | Alcatel-Lucent Usa Inc. | Chat-based support of communications and related functions |
EP3334099A1 (fr) * | 2015-08-06 | 2018-06-13 | Proyectos y Soluciones Tecnologicas Avanzadas, S.L | Système de messagerie instantanée |
EP3378204A1 (fr) * | 2016-09-20 | 2018-09-26 | Google LLC | Interaction avec un robot |
-
2021
- 2021-10-06 FR FR2110582A patent/FR3127828A1/fr not_active Withdrawn
-
2022
- 2022-10-05 WO PCT/EP2022/077658 patent/WO2023057492A1/fr active Application Filing
- 2022-10-05 EP EP22798131.3A patent/EP4413715A1/fr active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015109946A1 (fr) * | 2014-01-24 | 2015-07-30 | Tencent Technology (Shenzhen) Company Limited | Procédés et dispositifs de commande de machines |
US20160021038A1 (en) * | 2014-07-21 | 2016-01-21 | Alcatel-Lucent Usa Inc. | Chat-based support of communications and related functions |
EP3334099A1 (fr) * | 2015-08-06 | 2018-06-13 | Proyectos y Soluciones Tecnologicas Avanzadas, S.L | Système de messagerie instantanée |
EP3378204A1 (fr) * | 2016-09-20 | 2018-09-26 | Google LLC | Interaction avec un robot |
Also Published As
Publication number | Publication date |
---|---|
FR3127828A1 (fr) | 2023-04-07 |
EP4413715A1 (fr) | 2024-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Abdi et al. | Privacy norms for smart home personal assistants | |
US20210158234A1 (en) | Customer contact service with real-time agent assistance | |
JP7528328B2 (ja) | プライベート状態と非プライベート状態との間の遷移 | |
US20160328890A1 (en) | System and Method for Automotive Diagnostic Tool Data Collection and Analysis | |
Horvitz et al. | BusyBody: creating and fielding personalized models of the cost of interruption | |
EP3095067B1 (fr) | Filtrage de confidentialité pour des données utilisateur demandées, et modes de confidentialité activés selon le contexte | |
WO2021051031A1 (fr) | Techniques de composition de service automatisée adaptative et sensible au contexte pour l'apprentissage automatique (ml) | |
CN110321273A (zh) | 一种业务统计方法及装置 | |
US20080208579A1 (en) | Session recording and playback with selective information masking | |
CA2806732A1 (fr) | Systeme et procede d'analyse structuree collaborative | |
US10254945B1 (en) | Contextual state-based user interface format adaptation | |
US11288293B2 (en) | Methods and systems for ensuring quality of unstructured user input content | |
US20200302263A1 (en) | Bot systems and methods | |
US9756141B2 (en) | Media content consumption analytics | |
Ascencio et al. | Party strategy, candidate selection, and legislative behavior in Mexico | |
US20240171485A1 (en) | Standardizing analysis metrics across multiple devices | |
US11164575B2 (en) | Methods and systems for managing voice response systems to optimize responses | |
US12062368B1 (en) | Programmatic theme detection in contacts analytics service | |
EP4413715A1 (fr) | Agent conversationnel en interface entre une machine et des utilisateurs | |
Bickelhaupt et al. | Challenges and Opportunities of Future Vehicle Diagnostics in Software-Defined Vehicles | |
US20160283050A1 (en) | Adaptive tour interface engine | |
US20220004479A1 (en) | Diagnosing and resolving technical issues | |
Shlega et al. | Users, smart homes, and digital assistants: impact of technology experience and adoption | |
CA3199685A1 (fr) | Determination d'une contribution de participant a une conference | |
Campos et al. | A reference architecture for remote diagnostics and prognostics applications |
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: 22798131 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18698923 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022798131 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022798131 Country of ref document: EP Effective date: 20240506 |