Object transport system implementing at least one reusable smart mobile container and a conversational assistant.

Abstract

Title: Object transport system implementing at least one reusable smart mobile container and a conversational assistant. The invention relates to an object transport system enabling conversational exchange. According to the invention, such a system comprises at least one reusable smart mobile container for transporting objects (1) configured to capture initial data from an interlocutor; an identifier of the object present in the container; and a conversational intelligent agent (18) configured to: receive the initial data with the object identifier; perform a contextualized semantic analysis of the initial data in light of the object identifier; optionally produce a second contextualized data resulting from the semantic analysis; and optionally transmit the second data to at least one container; said container (1) being further configured to process the second received data.Figure to be published: 1.

Description

Title of the invention: Object transport system implementing at least one reusable smart mobile container and a conversational assistant. Field of the invention

[0001] The invention relates to the field of conversational artificial intelligence linked to connected objects, also known under the terminology of the Internet of Things and the acronym IoT (from the English “Internet of Things”).

[0002] More specifically, the invention relates to an intelligent container, intended for the transport of products, parts or objects.

[0003] The invention finds particular application in shipping packaging or parcels, used in the field of logistics transport for the delivery of products. State of the art

[0004] In the logistics sector, it is common practice to label a package to identify its destination, sort it, and direct it through logistics platforms to its recipient. This technique suffers from the need to multiply the number of labels depending on the number of logistics providers involved in the transport. Furthermore, this basic technique has numerous drawbacks related to the loss of the peeling label, legibility problems, and the inability to track the package between two identification points at logistics platforms. Consequently, many packages are lost, and some are stolen.

[0005] It then became apparent that it was necessary to use packaging equipped with an on-board electronic unit with a screen acting as a label and capable of transmitting position information to a monitoring platform, along the logistics route followed.

[0006] Finally, to strengthen the security of these packages, means of locking the packages have been added, allowing opening under specific conditions, in order to limit access to the authorized person, often the final recipient.

[0007] However, these developments in the packaging for shipping and transporting an object are not without drawbacks.

[0008] Indeed, as soon as a new type of labeling comes into use, it is necessary to review and reformulate the processes, to consider the nominal operation and the situations of processing errors in the supply chain.

[0009] Another disadvantage of such a technique is that it then requires training all professionals in the supply chain in this new, often specific use.

[0010] Another disadvantage of this technique is that when the recipient receives his package, although he has been able to track its progress, he has no information relating to its transport.

[0011] Objectives of the invention

[0012] The invention therefore aims in particular to overcome the disadvantages of the prior art mentioned above.

[0013] More specifically, the invention aims to provide an object transport system enabling conversational exchange between a user and the transport packaging.

[0014] An objective of the invention is also to provide such a technique which is simple to implement by the user.

[0015] Another objective of the invention is to provide such a technique which allows relevant exchanges with the user.

[0016] An objective of the invention is also to propose such a technique which allows a conversational exchange centered around the sender's profile.

[0017] Another objective of the invention is to provide such a technique which is reliable and safe for the user. Description of the invention

[0018] These objectives, as well as others which will appear subsequently, are achieved using an object transport system allowing a conversational exchange with an interlocutor.

[0019] Within the framework of the invention, the system comprises at least one reusable intelligent package for transporting objects, also referred to as a container adapted to hold an object and capable of conversing with an interlocutor. The package is configured so as to capture initial data;

[0020] the system also includes an object identifier, of the object contained in other words present in the container during the transport of said object.

[0021] The system further includes an intelligent conversational agent configured to: a) receive the first data coupled with the object identifier contained during transport in the container, the first data being transmitted by the container, the object identifier being transmitted further in such a way as to allow a conversational exchange relating to the transported object; b) perform a semantic analysis of the first data received, contextualized in light of the object identifier coupled with the first data, forming a semantic result; c) optionally produce a second contextualized piece of data resulting from the semantic analysis; d) optionally transmit the second piece of data to at least one container, in response to the first piece of data;

[0022] Furthermore, in this system, the container is configured to process the second data received.

[0023] Thus, in such a system, thanks to these technical characteristics it is possible for a user to become an interlocutor of the package and to initiate a conversation in which the container sends data to an intelligent agent which, after having semantically analyzed them, can respond with the result of its analysis.

[0024] According to a particularly advantageous embodiment of the invention, the intelligent conversational agent is configured to:

[0025] - select, a first set of initial conditions according to a criterion of selection, in a library or set of corpora of initial conditions;

[0026] - use the first set of initial conditions when producing the second piece of contextualized data.

[0027] Thanks to these technical characteristics, the input data volume of the model is significantly smaller, which also has the advantage of faster processing.

[0028] According to an advantageous embodiment of the invention, the selection criterion is a function of the object identifier, and / or the semantic result of the analysis of the first data.

[0029] Thanks to these technical features, the targeted data sought is targeted with a set of initial conditions chosen accordingly. This has the advantage of increasing the relevance of the answers to questions from the user of the smart package.

[0030] According to a preferred embodiment of the invention, the first set of initial conditions includes information relating to the transported object, to enable the intelligent conversational agent to hold a conversation related to said object.

[0031] Thanks to these technical characteristics, the reusable smart parcel for transporting objects can respond appropriately to questions from the recipient on all subjects relating to the product or object delivered.

[0032] In addition, the selection of a specialized corpus makes it possible to increase the reliability of the answers delivered and limit the phenomena of hallucination.

[0033] According to a particular embodiment of the invention, the intelligent conversational agent is configured to select, at least one second corpus of initial conditions specialized according to the selection criterion, from the library, the first corpus and at least one second corpus forming a corpus group.

[0034] According to an advantageous embodiment of the invention, the intelligent conversational agent is configured to:

[0035] - extract a subset of data from the corpus group using a filter based based on the selection criterion;

[0036] - use said subset of data in the production of the second data contextualized.

[0037] Thanks to these technical characteristics, the intelligent conversational agent can adapt to different situations. In particular, the intelligent conversational agent can handle cases where several objects are present in the delivered package. In such a situation, an object identifier is transmitted to it for each object included in the package. In this way, it can, for example, select a set of initial conditions per object. However, this should not be interpreted as a limitation, as the multiple selection of sets of conditions is linked to the simultaneous delivery of several objects in the same package.

[0038] According to a particular embodiment of the invention, the container is configured to:

[0039] - store the object identifier of the object present in the container, and

[0040] - attach the stored object identifier, coupled with the first data transmitted to the agent Intelligent conversational.

[0041] It is understood that the container is configured to store multiple object identifiers to cover the transport of multiple objects simultaneously.

[0042] According to an advantageous embodiment of the invention:

[0043] - the container is configured so as to categorize its interlocutor into a profile type of conversation and transmit the typical conversation profile to the intelligent conversational agent;

[0044] - the intelligent conversational agent being configured so as to adapt the analysis semantics based on the typical conversation profile.

[0045] Thanks to these technical characteristics, the intelligent conversational agent is able to target its responses according to the category of its interlocutor.

[0046] According to a particularly advantageous embodiment of the invention, the intelligent conversational agent is configured so as to limit the communication of information during the conversation to information relating to the secure transport of the object, if the typical conversation profile does not have the status of recipient of the container.

[0047] Thanks to these technical characteristics, the intelligent conversational agent can limit the dissemination of information about the delivered object to its recipient and thus prevent an actor in the delivery chain from becoming aware of its contents.

[0048] According to one embodiment, the invention also provides an object transport system comprising a fleet of containers.

[0049] Thanks to these technical characteristics, the system can benefit from the collection of information from all the containers making up the fleet. This makes it possible, for example, to improve responses relating to the use of reusable smart parcels for transporting objects.

[0050] According to one embodiment, the mobile container is a reusable smart packaging or parcel for shipping objects.

[0051] According to a preferred embodiment of the invention, the first and second data are so-called communication data which form a conversational exchange, and in which the first piece of data comes from a user of the container; The processing of the second piece of data by the container consists of communicating the second piece of data to the user. The intelligent conversational agent is further configured to: - retain contextual information from the conversational exchange, - use the contextual information during said semantic analysis.

[0052] Thanks to these features, a user can query the container in natural language and receive help and / or clarifications in return, also in natural language. Furthermore, the user can converse with the container through a series of linked questions and answers.

[0053] In addition, the intelligent conversational agent has the history of questions / answers exchanged with the user and thus it can refine its analysis in order to increase the accuracy of its answers.

[0054] According to an advantageous embodiment of the invention, the first data is a so-called information data, such as an identifier, a physical quantity, or an operating configuration.

[0055] Thanks to these characteristics, the intelligent conversational agent receives information about the container's context. This information can be simple, coupled, or combined to provide a variable level of precision in the information gathered. The first piece of information might, for example, include the internal and / or external temperature, the internal and / or external atmospheric pressure. It could also include information related to its movement, such as acceleration, or a position via satellite location. Thus, from the movement information, the intelligent conversational agent can deduce the Subjecting the container to shock, vibration, or a fall. In the case of a fall, the height of the fall and / or the acceleration can provide additional information.

[0056] Advantageously, the identifiers are identifiers specific to the application, or identifiers of a known type, such as that of a SIM ® card (English acronym for "Subscriber Identify Module"), or even an NFC ® code (English acronym for "Near-Field Communication").

[0057] According to a particularly advantageous embodiment of the invention, the second piece of data, resulting from the semantic analysis of the first piece of data, referred to as information, is a command applied by the container. Thanks to these characteristics, optionally, depending on the result of the semantic analysis, a second piece of data is generated and then sent to the container, which can then use it. Thus, the intelligent conversational agent can choose between sending a text or voice message and commanding various actions, including controlling an LED (Light Emitting Diode), a siren or a loudspeaker, a motor, a display screen, or a locking / unlocking device. For example, the intelligent conversational agent can command the LEDs to flash to attract the user's attention.

[0058] According to a preferred embodiment of the invention, the intelligent conversational agent is configured such that: - record the first piece of data, referred to as information, in a continuous learning parameter database; and - train a model of the intelligent conversational agent with the continuous learning parameters stored in said database.

[0059] Thanks to these characteristics, the intelligent conversational agent increases its knowledge base, so as to enrich its responses and / or improve their relevance.

[0060] According to a particular aspect of the invention, the drive is automatic.

[0061] According to a particularly advantageous embodiment of the invention, the training is a deep learning, in which each continuous learning parameter is associated with a positive or negative appreciation weighting of said parameter.

[0062] Thus, with the help of "machine learning" or "deep learning" type algorithms, the value of the training data is qualified, improving the reliability of subsequent semantic analyses.

[0063] According to one embodiment, the container includes an input means for said first communication data, which is a voice capture means and / or a text input means.

[0064] Thanks to these features, the user can query the container directly in natural language orally and / or use an input device, such as a touch or mechanical keyboard, or a stylus combined with handwriting recognition, to communicate with the container. According to a particular embodiment of the invention, the input device is an independent, proximity-based remote control, such as a smartphone. The smartphone then communicates using a proximity wireless communication device such as Bluetooth®, BLE® (Bluetooth Low Energy), or Wi-Fi®.

[0065] Thanks to these characteristics, it is possible to produce containers at reduced prices and thus broaden the target customer base of the product.

[0066] According to an advantageous embodiment of the invention, the system includes a means for textual transcription of said voice capture, so that the intelligent conversational agent receives first data in text format.

[0067] Thanks to these characteristics, using speech, the user can communicate with the container whose captured voice message is converted into a text message received by the intelligent conversational agent, and directly interpretable by a conversational artificial intelligence.

[0068] According to one embodiment, the container includes a means for sound reproduction and / or a means for displaying said second data referred to as communication data.

[0069] Thanks to these features, the user receives an answer to the query that he has indirectly submitted to the intelligent conversational agent through the container.

[0070] According to an advantageous embodiment of the invention, the system includes a means for speech-to-text transcription of the second communication input produced in text format by the intelligent conversational agent. Thanks to these features, the user receives a voice response.

[0071] According to one embodiment, the container is selected from a group comprising a piece of luggage, a reusable box.

[0072] Thus, in a new and unexpected way, a reusable box, a reusable logistics delivery package, an electronic logistics label intended to equip a single-use package and also luggage, such as a suitcase, allow a user to converse to obtain different types of information, including information facilitating the use of the container.

[0073] In a particularly advantageous embodiment of the invention, the intelligent conversational agent is integrated into an embedded computer unit of said container and / or on a central computer platform configured to communicate with said container.

[0074] Thanks to these characteristics, it is possible to have either an autonomous container with localized intelligence, or a container supported by intelligence located on a remote central computing platform. It is also possible to distribute, or even combine, intelligence between the central computing platform and the container, to increase the relevance and / or speed of responses, or to distribute the processing load according to the processing power capacity of the container.

[0075] In addition, localized intelligence in each container also offers the advantage, particularly in the case of luggage, of improving confidentiality and / or respect for privacy.

[0076] Furthermore, such localized intelligence compensates for the lack of connectivity with the central computing platform in the event of a failure of long-distance communication means. This also makes it possible to reduce the energy consumption of the long-distance communication module. It also allows for the management and therefore minimization of 4G data consumption.

[0077] According to a particular embodiment of the invention, the intelligent conversational agent is deployed on an externalized computing platform configured to communicate with said central computing platform. Furthermore, the intelligent conversational agent and the container are configured to communicate with each other via the central computing platform.

[0078] Thanks to these characteristics, the intelligent conversational agent is deployed on an externalized platform at a specialized provider, for example.

[0079] According to a particular embodiment of the invention, the transport system further comprises a means of communication with a global computer network. According to alternative embodiments, the means of communication connects the central computing platform and / or the externalized computing platform to the global computer network.

[0080] Thanks to these characteristics, the intelligent conversational agent is able to supplement its learning by consulting the internet. Furthermore, it can enrich its responses with information collected from the global computer network, such as weather information related to a temperature spike recorded by the container in a specific location.

[0081] According to an advantageous embodiment of the invention:

[0082] - the container is configured so as to identify the user, categorize the user identified in a typical conversation profile and transmit the typical conversation profile to the intelligent conversational agent;

[0083] - the intelligent conversational agent being configured so as to adapt the analysis semantics based on the typical conversation profile.

[0084] Thanks to these features, the intelligent conversational agent is able to provide targeted information based on the typical conversation profile and therefore the user's role, which could be that of a customer receiving a package, a logistics professional responsible for its delivery, or an agent in charge of maintaining the reusable package. Thus, the identified maintenance agent can, using voice command keywords, obtain diagnostic information, or information and recommendations from the after-sales service manual, which are not available to other roles.

[0085] According to one embodiment of the invention, user identification is supplemented by authentication.

[0086] Thus, thanks to this technique, it is possible to ensure, for example, that only the receiving customer can obtain the opening of the container upon delivery.

[0087] According to a particularly advantageous embodiment of the invention, the intelligent conversational agent is configured to choose a conversational language based on the container's position, received in the first piece of information. This position, which is a physical location variable, is typically the container's last GPS position. However, it can also be deduced from other information, such as the current cell phone signal strength, or the known location of the current storage warehouse and / or its Wi-Fi® network to which the container can be connected.

[0088] Thus, the intelligent conversational agent engages in dialogue in the local language when it is available, or switches to an international language, typically English, or Spanish, or French.

[0089] Advantageously, the intelligent conversational agent uses the location position to determine local culture criteria and adapt the responses produced to these criteria.

[0090] Certain aspects of the invention are based on the idea of ​​implementing advances in artificial intelligence in the conversational field, in particular with large language models or LLMs (English acronym for "Large Language Model"), of the type of "pre-trained generative transformers", such as services like GPT3 ® and ChatGPT ® from OpenAI ®, Bert ® and Bard ® from Google ®, or even with generative artificial intelligence.

[0091] These aspects of the invention encompass the idea of ​​being able to quickly and easily adapt, or even update, the responses to be given to the interlocutor, depending, in particular, on the object being transported. Other aspects of the invention incorporate the idea of ​​significantly optimizing the relevance of these responses, so as to provide a high level of accuracy in them.

[0092] One objective of the invention is to provide a reliable technique that, consequently, reduces the risk of hallucination in the responses provided. As a reminder, in artificial intelligence, hallucination occurs when a statistically plausible but erroneous response is given to a user who might mistakenly believe it to be a real or certain fact.

[0093] Advantageously, the invention uses Retrieval Augmented Generators (RAGs). Such optimization of generative artificial intelligence is implemented using well-known technological building blocks for those skilled in the art, such as Microsoft's AutoGen®, Langchain Inc.'s Langchain®, and Llamalndex®, cited by way of illustrative and non-limiting examples.

[0094] Thus, the use of such techniques offers numerous advantages. It improves the efficiency of LLM processing by enabling the use of significantly, even considerably, smaller databases. It also provides greater flexibility for creating new corpora or adding new documents. Furthermore, it increases the reliability of the results through better control of the knowledge base and mastery of the document sources used, thereby reducing the risk of hallucination in the responses provided. Such use also contributes to improved confidence in the responses, due to the aforementioned advantages. Presentation of the figures

[0095] Other features and advantages of the invention will become more apparent upon reading the following description of embodiments of the invention, given by way of simple illustrative and non-limiting examples, and the accompanying drawings, among which: - [Fig.1] [Fig.1] is a schematic representation of an example embodiment of an object transport system representing a communicating container according to the invention; - [Fig.2] [Fig.2] is a schematic representation of a second example of an embodiment of smart luggage according to the invention. Detailed description of the invention 1. Example of an embodiment of the invention

[0096] A first embodiment of an object transport system according to the invention, comprising a container 1, a computer infrastructure 14 and an externalized computer platform 19, is illustrated in [Fig.1].

[0097] The container 1 enabling conversational exchange integrates electronic means including an embedded computer unit 2, and storage means data 3, a power supply battery 4, a microphone 5, a speaker 6, a digital display 7, one or more control buttons 8, a first means of communication 9, one or more actuators not shown, all assembled according to techniques known per se.

[0098] It also incorporates a multitude of sensors (not shown) to obtain various information related to its storage, transport, or environment. Thus, it can obtain a GPS (Global Positioning System) position, allowing its movement to be tracked, motion information, and infer whether it has absorbed an impact, whether it is subjected to vibrations, or even record a fall. Container 1 is also capable of recording internal and / or external information such as temperature and atmospheric pressure. This various information also includes an identifier specific to container 1, an identifier specific to the computer unit 2, a SIM card identifier (Subscriber Identify Module), a Near Field Communication (NFC) code, or any other identifier known to those skilled in the art..

[0099] The computer infrastructure 14 includes a computer platform 15, a database 16 and a second means of communication 17 for communicating via the first means of communication 9, with the computer unit 2 of the container 1.

[0100] Furthermore, the IT infrastructure 14 is capable of communicating using a third means of communication 20 with the outsourced IT platform 19.

[0101] In this embodiment, the outsourced computing platform 19 includes a conversational artificial intelligence module, typically software-based, which constitutes a conversational agent 18 configured to:

[0102] a) receive captured data, transmitted by container 1 via IT infrastructure 14; b) perform a semantic analysis of the captured data; c) produce data resulting from the semantic analysis; and d) transmit, via the IT infrastructure 14, the resulting data to container 1;

[0103] A conversation begins when the captured data is a first piece of communication data, and the resulting data is a second piece of communication data. In this case, the first and second pieces of communication data are stored by the conversational agent 18 using methods known per se, to retain contextual information. This is then, a conversation history composed of this contextual information which is enriched as the exchanges progress.

[0104] To initiate a conversation, a user presses button 8 on container 1. The computer unit then triggers audio capture using microphone 5 and records the voice message emitted by the user. It then transmits this voice message, called the first captured voice message, to the computer infrastructure 14. This infrastructure, equipped with speech-to-text conversion means known in English as "speech-to-text" and "text-to-speech," transcribes the first voice message into a corresponding first text message. The computer infrastructure 14 then transmits this first text message to the conversational agent 18 on the externalized computer platform 19.

[0105] In a conversation, the resulting data, which is a second text message, is first received by the computer infrastructure 14. This infrastructure converts the second text message into a second voice message and transmits it to the container 1. Then, the container 1 broadcasts the second voice message through the speaker 6 to the user, who can continue the conversation. Thus, through this chain of exchanges, the container 1 supports the conversation with the user.

[0106] Furthermore, being equipped with other information sources specified above, container 1 is also configured to transmit at least one of the various pieces of information available as a captured data message. For example, the captured data transmitted may carry its GPS position. Or the captured data may contain a combination of information, such as the identifier, the internal temperature, and the external temperature measured by container 1.

[0107] When the captured data is not the user's voice message but rather informational data, the resulting data is a command transmitted to the container 1, which applies it to at least one of the actuators. For example, the resulting command unlocks the container 1, allowing the user to open it. However, the user's voice message may be interpreted by the conversational agent 18 as a command to one of the actuators. Nevertheless, depending on the configuration of the container 1 and / or the conversational agent 18, the user may not necessarily be able to act on all the actuators equipping the container 1.

[0108] In the context of the object transport system, using a fleet of containers 1, it is the set of data sent back by the fleet of containers to the conversational agent 18 that contributes to the enrichment of the model.

[0109] Furthermore, contextualizing container 1 allows the conversation to be guided in order to provide the user with the most appropriate information possible in relation to container 1 and in particular its possibilities.

[0110] In addition, contextual information is fed into the learning of the conversational agent model 18, so as to provide it with a set of initial conditions. Typically, this contextual information relates to the container 1, its description, its instructions for use, possible uses, frequently asked questions submitted by users, the commercial offer for transporting objects using the container 1, or information about the company managing the fleet of containers 1 forming the object transport system.

[0111] For this purpose, the conversational agent 18 is subjected to a specialization of its model in which it is provided with a series of keywords and the associated semantics to form the corpus of initial conditions.

[0112] By way of example, learning the events associated with a transmission can be done according to the following illustrative pseudo-code:

[0113] “Each stored event is composed of type, value where date is the date of the event, type is the type of the event and value is defined per type as foliow:

[0114] -'sender': name, address

[0115] - 'recipienfmame, address

[0116] - 'startShipmenf: date, latitude, longitude

[0117] - 'endShipmenf: date, latitude, longitude

[0118] - 'sensors': date, 'extemalTemperature', measure (in °C), 'internalTemperature', measure (in °C), 'externalHumidity', measure (in %), 'intemalHumidity', measure (in %), 'pressure', measure (in hPa)

[0119] - 'geolocation': date, latitude, longitude

[0120] - 'warehouse': enterDate, exitDate, latitude, longitude, name

[0121] - 'flighf : fromDate, fromLatitude, fromLongitude, fromAirport, toDate, toLatitude, toLongitude, toAirport

[0122] - 'alerf : date, latitude, longitude, subtype (in 'extemalTemperature', 'intemalTemperature', 'externalHumidity', 'intemalHumidity', 'freeFall'), measure

[0123] -'events': You will return every events containing the keyword 'store' as a list without displaying the keyword itself. When 'evenf is followed by a type, return every events of the defined type as a list instead of ail 'store' keywords and return the closest city instead of raw location coordinates. »

[0124] The learning of the associated semantics can be carried out in the following way:

[0125] “A duration between two events event A and event B is defined as the difference between the date of the event B and the date of the event A.

[0126] The duration of an event is defined as the difference between the exitDate and the enterDate of the event or the toDate and the fromDate of the event”

[0127] The container 1 is for example a parcel or shipping packaging according to the invention.

[0128] A contextualization principle centered on the use of the container has been previously described. In this example, the corpus of initial conditions contains all, or at least all, information about the container deemed useful for answering the user's questions on this subject. In this case, the contextual information then includes this type of corpus of initial conditions, specialized in information relating to the container and the history of questions / answers exchanged with the interlocutor or user. Furthermore, a corpus of initial conditions concerning the shipment of the container has also been described, notably taking into account information gathered by container 1 and / or by the fleet of container 1.

[0129] However, this principle of contextualization is only an illustrative example and should not be understood as a definitive assertion. Thus, other types of corpora are included within the scope of the invention.

[0130] According to a particularly advantageous embodiment, the container 1, in the form of an intelligent reusable shipping package, possesses information about the object or product it contains and transports. Thus, the contextual information can relate to all information dedicated to the object or product to be transported, contributing to the formation of a specific set of initial conditions, used by the conversational agent model 18.

[0131] By way of illustrative and non-limiting examples, this information on the shipped item may include the detailed characteristics of the item, whether its technical or aesthetic characteristics, its advantages, possibly its disadvantages or limitations, but also its implementation or a detailed instruction manual for the item.

[0132] In other words, the IT infrastructure 14 and / or the container 1 stores an object identifier for each object present during shipment in the container 1's storage volume. By communicating each object identifier to the conversational agent model 18, the latter determines, from a library also called a set of initial conditions, the corpus of contextual data to be used. It is understood that, for this embodiment, a corpus of initial conditions is dedicated to a particular object. In this case, the corpus of initial conditions is then specialized. In other words, the conversational agent 18 chooses, from a set of initial conditions corpora, or library, which covers a set of objects, without necessarily linking them, the corpus of initial conditions relevant to the transported object using the object identifier serving as the selection criterion.

[0133] It is important to understand that a set of initial conditions can cover a broader scope than a single object, for example, including the description of a A product range or product catalog listing all the products available for sale from a vendor. Clearly, information used to enrich a corpus can also come from the user manual of a previously mentioned product, or from lists of recommended products or services directly or indirectly related to the product being transported, such as recommended maintenance or care instructions.

[0134] Thus, thanks to knowledge of the transported product, via the object identifier on the one hand and the contextual information specific to this product aggregated in the conversational agent model 18 on the other hand, the container 1 can hold a conversation about the object it carries. It can inform a recipient about the product they are receiving, based on a knowledge base far superior to that assimilated by a human interlocutor, in the role of a sales agent, a technical contact, or an after-sales service contact, for example.In the case of a gourmet product, such as a fine wine, the recipient, upon receipt and during a conversation, can obtain advice and information about the wine received, such as its organoleptic properties, other characteristics, food pairings, aging potential, storage conditions, and serving suggestions. This information or conversation may include usage tips, arguments or advantages, or even congratulations on the wise choice of purchasing the product.

[0135] For this purpose, for example, the container 1 receives the identification information of the product it contains from a remote server, typically the IT infrastructure 14. Alternatively, using its onboard image sensor directed towards the internal volume of the container suitable for receiving the product or object, the container captures at least one image so as to identify the product or object. This identification is obtained by any means known to those skilled in the art, including image recognition techniques performed by the IT infrastructure 14, for example. Any other known method is applicable to allow the container to retrieve the identifier of the object it carries, in particular via a tag associated with the object which transmits its identifier using a near-field communication technique.

[0136] Thus, container 1 and / or the IT infrastructure 14 are capable of correlating the contextual information corresponding to the product present in container 1. This identifier is coupled by container 1 and / or the IT infrastructure 14 to the first communication data received by the chatbot 18. In summary, the question asked by the interlocutor of container 1 is transmitted in the form of the first data associated with the object identifier to the chatbot 18, which provides a response via the second communication data. This response provides information about the object, product, transported when the question relates to this subject.

[0137] It is perfectly clear and understood within the framework of this invention that at any time during the journey, i.e. the transport of the container 1, the information brought up by the container and aggregated in the conversational agent model 18 can be communicated, in whole or in part, to the participants in the logistics chain, to the sender or to the recipient.

[0138] However, if confidentiality is required, the information remains shared between the current user and the chatbot 18. The record of this contextual information is then not retained after delivery. In other words, the object identifier in this particular circumstance is deleted from the location(s) where it was stored. The link between this object identifier and the customer during this delivery does not persist and therefore no longer exists.

[0139] Furthermore, only information relating to the safety of goods and people is available for conversation with the various actors in the logistics chain during transport. Apart from this safety information, all other information is only available to support a conversation with the clearly identified recipient of Container 1, a reusable smart package. In other words, the type of person initiating a conversation is identified and then classified or categorized within a typical conversation profile to ensure they are indeed the recipient of Container 1 before providing them with information revealing the nature of the transported item. In other words, only the recipients of the package receive information about the item they are receiving during a conversation.Therefore, once the package has been shipped, only the recipients can obtain all the information available in the set of initial conditions corresponding to the delivered product.

[0140] In a variant of the previous embodiment, the conversational agent 18 selects several corpora of initial conditions from the library, forming a group of selected corpora. This selection is also based on a selection criterion, which is the received object identifier. This selection criterion can also be based on the question asked, or on a combination of the question and the object identifier associated with the question. It is clear that when the question asked is taken into account in the selection criterion, it is the semantic analysis of the question that is included in the parameters of the selection criterion. Furthermore, the selection of several corpora of initial conditions is followed by a step of selecting a portion of the data from the group of corpora, which forms a subset of extracted data.In other words, this step involves filtering the data present in the corpus group using a filter based on the previously defined selection criterion. In this variant, it is ultimately this subset of extracted data correlated with . the history of questions / answers exchanged with the user that the intelligent conversational agent uses to produce its response.

[0141] Consequently, the use of a library or set of corpora makes it possible to adapt the implementation strategy and thus choose between pooling or compartmentalizing the data of the different corpora according to the confidentiality requirements required according to the products transported.

[0142] 2. Other examples of embodiments of the invention

[0143] In [Fig.2], the container 1 has been represented as a piece of luggage, here a suitcase 10 forms an object transport system according to a second embodiment of the invention.

[0144] The container 1 also includes electronic means, including the embedded computer unit 2, the data storage means 3, the power supply battery 4, the microphone 5, the loudspeaker 6, and the button 8, assembled according to techniques known per se. The embedded computer unit 2 of the case 10 is configured to capture, using the microphone 5, requests formulated by the user of the case 10 and to transmit responses via the loudspeaker 6. Thus, the microphone 5 and the loudspeaker 6 form an interface with the user of the case 10.

[0145] In addition, the embedded computer unit 2 is configured to run the intelligent conversational agent, and thus autonomously maintain a conversation with the user of the suitcase 10.

[0146] Furthermore, the embedded computer unit 2, thanks to the communication means 9, is capable of receiving a specialized corpus chosen according to the intended use of the suitcase 10. For example, this corpus is specialized according to a particular journey, with information on scheduled transit locations such as train stations, airports, a city's transport infrastructure with information on the subway station map, etc. Thus, the user can, through a conversation with the suitcase 10, obtain information to find their way through the maze of corridors in these transit locations.

[0147] In a variant of the second embodiment, the embedded computer unit 2 communicates via the communication means 9 with the remote conversational intelligent agent 18 on the computer infrastructure 14, or on the outsourced computer platform 19, not shown.

[0148] Within the framework of the invention, it is obviously planned to apply the principle, described in the previous chapter, of conversation about the object contained in a container 1 of the type intelligent shipping parcel, to the luggage illustrated by [Fig.2].

[0149] Thus, based on the same operation, the owner of the luggage has the role of recipient of a package and becomes the interlocutor of the intelligent conversational agent 18.

[0150] In this case, the owner can record the baggage information about the object or product it contains when this cannot be obtained using the methods described above. Thus, the object identifier is known, usable, and can be linked to the first communication data as already described.

[0151] When luggage is used by its owner / seller to present products, such as new samples of medical prostheses or new medications, the intelligent conversational agent 18 can, by selecting the appropriate set of initial conditions, hold a conversation with a healthcare professional—doctor or surgeon—to provide them with all the specific information about the product being presented. This eliminates any unanswered questions that the representative could not have addressed immediately. This time saving increases the relevance of sales interactions and avoids having to contact overworked professionals again to provide details that the seller could not have supplied themselves.

[0152] 3. Other optional features and advantages of the invention

[0153] In variants of the embodiments of the invention detailed above, it may also be provided that: - to record, at the level of the conversational agent 18, the data captured in a continuous learning parameter storage database, when the data captured is at least one of the miscellaneous pieces of information, so as to train a model of said conversational agent 18, according to a technique known under the English terminology of "machine learning". Thus, the conversational agent 18 is capable of training its model on the one hand and is configured to train it automatically on the other hand; - to associate the captured data with a positive or negative appreciation weighting, taken into account by the conversational agent model 18. Thus, the model training is a deep learning technique, known in English as "deep learning". This increases the statistical analysis performance of the model and consequently the relevance of conversational exchanges with the user; - to integrate into the container means of user identification and / or authentication to determine their role and consequently the conversation profile to adopt. Identification can be obtained by any known method, such as a badge, a means of voice recognition, etc.; - to integrate the means of voice-to-text conversion into container 1, or to move these means to the externalized platform, or even to a specialized supplier. - to integrate the conversational agent 18 into the IT infrastructure 14, optimizing in particular response times; to embed the conversational agent 18 in the computer unit 2 of the container 1 serving as shipping packaging, and thus give it autonomy to converse with the user; for the conversational agent 18 embedded in the computer unit 2, to receive continuous learning parameters possibly weighted, issued by the computer infrastructure 14, the learning parameters relating to the feedback from a fleet of container 1 in operation; to specialize the intelligent conversational agent so that it adapts its semantic analysis according to the current location of the container; to transmit an instruction, in other words a voice message to the user, following the analysis of captured data, for example to issue a message requiring more precautions in the handling of container 1 when a fall is detected; to use a digital touchscreen as an input and / or output interface between container 1 and the user; to integrate the first means of communication 9 with the electronic means of the suitcase 10; to create dedicated fleets per customer of a logistics carrier, with a compartmentalization of the contextualization and therefore of the initial corpus used by the conversational agent 18 according to the specificities of the customer; to use, for example, a serial number of the transported object as an identifier of the object; to provide a specialized corpus based on a particular journey, with information on programmed transit locations such as train stations, airports, transport infrastructure of a city, to facilitate the transport of a parcel 1; that the object identifier is considered as a second identifier within the meaning of the invention, when all the other identifiers previously mentioned are considered as a first identifier such as for example the identifier of a SIM ® card (English acronym for "Subscriber Identify Module"), or that of an NFC ® code (English acronym for "Near-Field Communication"); that all previously defined and / or cited identifiers, including application-specific identifiers, are usable by the intelligent conversational agent; that a library or set of corpora of initial conditions is not necessarily fixed, but can be dynamically constituted and / or enriched according to needs; - that each user of the package, throughout the logistics chain, from sender to recipient, is an interlocutor willing to engage in a conversation with the intelligent conversational agent.

[0154] The technique described above for creating an object transport system enabling conversational exchange can be used with different types of receptacles, for example to constitute a container of the type used for transporting goods.

[0155] It should be understood that the elements shown in the figures can be implemented in various forms of hardware, software, or combinations thereof. Preferably, these elements are implemented in a combination of hardware and software on one or more appropriately programmed multipurpose devices, which may include a processor, memory, and input / output interfaces.

[0156] The present description illustrates the principles of this disclosure. It will therefore be appreciated if persons skilled in the art will be able to devise various arrangements which, although not explicitly described or shown here, embody the principles of the disclosure and are included within its scope.

[0157] Thus, according to the principle of the invention, it is important to understand that the library or libraries, or set of corpora of initial conditions, allow the selection of at least one corpus of contextual data that serves as the basis for the conversational agent to support a conversation with the user. This library or these libraries can be enriched and / or specialized according to the needs of the operator of the object transport system, or other stakeholders such as the sender, and thus broaden the possible discussion contexts beyond the examples described above.

[0158] All examples and conditional language cited herein are intended for educational purposes to assist the reader in understanding the principles of disclosure and the concepts introduced by the inventor to advance the art, and should be interpreted as not being limited to those specifically cited examples and conditions.

[0159] Furthermore, all statements of principles, aspects, and implementation methods of disclosure, as well as specific examples thereof, are intended to encompass their structural and functional equivalents. Moreover, it is intended that these equivalents will include both currently known equivalents and equivalents developed in the future—that is, any developed element that performs the same function, regardless of its structure.

[0160] Thus, for example, those skilled in the art will understand that the schematic diagrams presented here represent conceptual views of illustrative circuits implementing the principles of disclosure. Similarly, it will be appreciated that all the Organizational charts, flowcharts, and the like represent various processes that can essentially be represented on a computer-readable medium and thus executed by a computer or processor, whether or not that computer or processor is explicitly represented.

[0161] Insofar as embodiments of the invention have been described as being implemented, at least in part, by a software-controlled data processing device, it will be understood that a machine-readable non-transient medium carrying such software, such as an optical disc, a magnetic disc, a semiconductor memory or the like, is also considered to represent an embodiment of the present invention.

[0162] The functions of the various elements illustrated in the figures can be performed using dedicated hardware as well as hardware capable of running software in conjunction with suitable software. When performed by a processor, the functions can be performed by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared. Furthermore, the explicit use of the term "processor" or "controller" should not be interpreted as referring exclusively to hardware capable of running software, and may implicitly include, without limitation, a digital signal processor (DSP), read-only memory (ROM) for storing the software, random-access memory (RAM), and non-volatile storage media.In addition, some elements can be independent or grouped together, for example in a microcontroller (MCU), or a system-on-a-chip (SoC).

[0163] Other hardware, conventional and / or custom, may also be included. Similarly, all switches shown in the figures are purely conceptual. Their function may be performed by the operation of program logic, by dedicated logic, by the interaction of a program control and dedicated logic, or even manually, the particular technique being selectable by the operator as more specifically understood in the context.

[0164] In the claims of this document, any element expressed as a means of performing a specified function is intended to encompass any way of performing that function, including, for example, a) a combination of circuit elements that performs that function or b) software in any form, including, therefore, firmware, microcode, or the like, combined with appropriate circuitry to execute that software in order to perform the function. The disclosure as defined by such claims lies in the fact that the functionalities provided by the various means cited are combined and brought together from the in the manner specified in the claims. Therefore, all means that can provide these functionalities are considered equivalent to those presented here.

Claims

Demands

1. An object transport system enabling conversational exchange with an interlocutor, comprising: - at least one intelligent mobile object transport container capable of containing an object and capable of conversing with an interlocutor, the container being configured to capture first data; - an object identifier of the object contained by said container (1) during the transport of said object; and - an intelligent conversational agent (18) configured to: a) receive the first data coupled with said object identifier contained during transport in the container, the first data being transmitted by said container, the object identifier being further transmitted in such a way as to enable conversational exchange relating to the transported object; b) perform a semantic analysis of said first data received, contextualized in light of the object identifier coupled with said first data, forming a semantic result;c) optionally produce a second contextualized data item resulting from the semantic analysis; d) transmit said second data item to at least one container in response to said first data item when the second data item is produced in step c); said container being further configured to process the second data item received.

2. Object transport system according to claim 1, wherein the intelligent conversational agent (18) is configured to: - select, a first corpus of initial conditions according to a selection criterion, from a library or set of corpora of initial conditions; - use the first corpus of initial conditions when producing the second contextualized data.

3. Object transport system according to claim 2, wherein the selection criterion is a function of the object identifier, and / or the semantic result of the analysis of the first data.

4. A system for transporting objects according to claims 2 or 3, wherein said first set of initial conditions comprises information relating to said transported object, to enable the agent Intelligent conversational system to maintain a conversation related to the said object.

5. Object transport system according to any one of claims 1 to 4, wherein the intelligent conversational agent (18) is configured to select, at least one second corpus of initial conditions specialized according to the selection criterion, from the library, the first corpus and at least one second corpus forming a corpus group.

6. Object transport system according to claim 5, wherein the intelligent conversational agent is configured to: - extract a subset of data from the corpus group using a filter based on the selection criterion; - use said subset of data in the production of the second contextualized data.

7. Object transport system according to any one of the preceding claims, wherein the container (1) is configured to: - store the object identifier of the object present in the container, and - attach the stored object identifier, coupled with the first data transmitted to the intelligent conversational agent (18).

8. A system for transporting objects according to any one of the preceding claims, comprising a fleet of containers.

9. Object transport system according to any one of the preceding claims, wherein: - the container is configured so as to categorize its interlocutor into a typical conversation profile and transmit the typical conversation profile to the intelligent conversational agent; - the intelligent conversational agent being configured so as to adapt the semantic analysis according to the typical conversation profile.

10. Object transport system according to the preceding claim, wherein the intelligent conversational agent (18) is configured to limit the communication of information during the conversation to information relating to the secure transport of the object, if the typical conversation profile does not have the status of recipient of the container (1).

11. An object transport system according to any one of the preceding claims, wherein the first and second data are so-called communication data that form a conversational exchange, and in which said first data comes from the interlocutor of said container; said processing of the second data by the container consists of communicating said second data to said interlocutor, the intelligent conversational agent is further configured so as to: - retain contextual information from the conversational exchange, - use the contextual information during said semantic analysis.

12. Object transport system according to any one of the preceding claims, wherein the intelligent conversational agent is configured to choose a conversation language based on a geographical position of the container.

13. Object transport system according to any one of the preceding claims, wherein the intelligent conversational agent is integrated into an embedded computing unit (2) of said container and / or on a central computing platform (14) configured to communicate with said container.

14. Object transport system according to claim 13, wherein the intelligent conversational agent is deported to an externalized computing platform (19) configured to communicate with said central computing platform, the intelligent conversational agent (18) and the container (1) being configured to communicate with each other via the central computing platform.

15. Object transport system according to any one of the preceding claims, wherein the mobile container is a reusable intelligent object shipping package (1).

Images