Method of communication with a computer system comprising a knowledge base

Abstract

The invention relates to a method of communication with a computer device (CD) comprising a knowledge base (KB) modeling data in the form of a knowledge graph (KG), said method comprising the following, at the level of said device: - receiving (S1b) a first request (REQ1) comprising information relating to an entity (ENT) of the knowledge graph, - requesting (S2) the rendering of a web page containing said information, - receiving (S3b) a second request (REQ2) requesting at least one missing property of said entity, from among said rendered information, - requesting (S4) the rendering of a web page containing a list of missing properties ranked by frequency of observation of these properties for other entities of the same type, - querying (S5-S7) a language model, from a prompt generated in natural language by said device,said prompt asking the language model what the value (V) of at least one of the properties in the list is, - command (S8) the rendering of a web page containing said value. Figure 3A,

Description

Title of the invention: Method for communicating with a computer device comprising a knowledge base. Field of the invention

[0001] The field of the invention is that of querying databases. More specifically, the present invention relates to a method of communicating with a computer system (computer, server, platform, etc.) comprising a knowledge base modeling data in the form of a knowledge graph, for the purpose of enriching the information contained in the knowledge graph. The present invention also relates to the computer system, a corresponding computer program, and a storage medium. Previous art

[0002] Among knowledge graph construction techniques, collaborative construction involving human contributors remains important, as exemplified by the Wikidata knowledge graph, a reference for many domains and use cases. This collaborative construction is currently carried out primarily manually, making the graph building process lengthy and tedious, particularly when the knowledge domains are vast. Furthermore, the knowledge graph information resulting from this manual construction may not always be reliable or legitimate.

[0003] There are also techniques for enriching knowledge graphs using generative artificial intelligence systems of the broad language model type. Language models are queried using a prompt to retrieve missing knowledge in a knowledge graph for an entity to be enriched. However, such a technique requires sending queries to the language model in all directions, without any preconception of the desirable properties of the entity to be enriched. Using a language model when implementing such a technique is therefore very expensive because it requires numerous inferences to generate missing properties that are not necessarily relevant to the entity to be enriched.As a result, the information used to enrich the knowledge graph is sometimes inaccurate and inconsistent, which greatly undermines the reliability of this enrichment technique. Object and summary of the invention.

[0004] One of the aims of the invention is to remedy at least one of the drawbacks of the aforementioned prior art by proposing a new, more efficient technique for enriching a knowledge graph, particularly from the point of view cost in computing resources and energy consumption, and reduction of hallucinations.

[0005] To this end, an object of the present invention relates to a method of communication with a computer device comprising a knowledge base modeling data in the form of a knowledge graph, such a method comprising the following, at the device level:

[0006] - receive a first request including information relating to an entity of the knowledge graph,

[0007] - to order the rendering of a web page containing said information,

[0008] - receive a second request asking for at least one missing property of the entity, among the aforementioned information provided,

[0009] - command the rendering of a web page containing a list of properties missing properties, ranked by frequency of observation of these properties for other entities of the same type,

[0010] - querying a language model, from a prompt generated in natural language through the device, the prompt asks the language model what the value of at least one of the properties in the list is,

[0011] - command the rendering of a web page containing this value.

[0012] The invention allows, during the enrichment phase of a knowledge graph, the automatic generation by the computer system, for a language model, of one or more adapted and targeted prompts. Such prompts are generated only with respect to missing properties that have been previously identified as relevant to the entity, thus limiting the risk of hallucinations regarding properties irrelevant to that entity. Thanks to the use of such a language model:

[0013] - the number of human operations to enrich a knowledge graph is significantly limited compared to prior art solutions for collaborative knowledge graph enrichment, which reduces errors that can occur during enrichment, lightens the user workload, and accelerates the enrichment phase,

[0014] - to significantly reduce the number of inferences generated by the device computer science to generate properties, which, in the case of some prior art solutions based on generative AI tools, are not necessarily relevant to the entity to be enriched because they result from sending many requests without any prior knowledge of the desirable properties for the entity to be enriched.

[0015] The invention thus makes it possible to propose a more efficient knowledge graph enrichment technique because it is faster, less expensive, and less energy-intensive than classical knowledge graph enrichment techniques.

[0016] According to a particular embodiment, the prompt is generated for a number of properties in the list which is determined with respect to a threshold of observation frequency of these properties in the knowledge base, for at least one other entity of the same type as the entity.

[0017] Given that prompts are generated for a number of properties determined in relation to a required observation frequency threshold, the language model is thus used in a more limited way, since fewer prompts will be generated by the computer device, which makes it possible to optimize the reduction of the energy footprint and the cost of the enrichment technique of the invention.

[0018] According to another particular embodiment, the observation frequency threshold is defined prior to the implementation of the communication process or is contained in a third request received by the device, in response to the rendering of the web page containing the list of missing properties.

[0019] Such an embodiment makes it possible to enrich a knowledge graph in an adaptive and customizable way by a user of the computer device.

[0020] According to another particular embodiment, the communication method comprises the following:

[0021] - receive a selection of a validation or non-validation of said value contained in the web page rendered using a human-machine interface,

[0022] - add said value to the knowledge graph, in association with said entity, if Validation of the value is requested.

[0023] Such an embodiment makes it possible to offer a user of the computer device a simplified enrichment interface which greatly facilitates the manual operations of enriching a knowledge graph.

[0024] According to another particular embodiment, said value relates to a data property or an object property.

[0025] Such an embodiment makes it possible to enrich the knowledge graph with data of different kinds, which makes it possible to enrich a knowledge graph in a precise and complete manner.

[0026] The various modes or embodiments mentioned above can be added independently or in combination with each other to the communication process as defined above.

[0027] The invention also relates to a computer device comprising a knowledge base modeling data in the form of a knowledge graph, the device being characterized in that it is configured to implement:

[0028] - receiving an initial request containing information relating to a entity of the knowledge graph,

[0029] - a command to render a web page containing said information,

[0030] - receiving a second request requesting at least one property missing from said entity, among said information returned,

[0031] - a command to render a web page containing a list of properties missing properties, ranked by frequency of observation of these properties for other entities of the same type,

[0032] - querying a language model, from a prompt generated in language natural by the said device, the said prompt asking the language model what the value of at least one of the properties of the list is,

[0033] - a command to render a web page containing said value.

[0034] Such a device is notably configured to implement the aforementioned communication process, according to one or the other of its embodiments.

[0035] The invention also relates to a computer program comprising instructions for implementing the communication method according to the invention, according to any one of the particular embodiments described above, when said program is executed by a processor.

[0036] Such instructions can be stored permanently in a non-transient memory medium of the computer device implementing the communication method according to the invention.

[0037] This program may use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0038] The invention also relates to a recording medium or information medium readable by a computer, and comprising instructions for a computer program as mentioned above.

[0039] The recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording means, for example a mobile medium, a hard disk drive or an SSD.

[0040] On the other hand, the recording medium can be a transmissible medium such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by radio, or by other means, so that the computer program it contains is executable remotely. The program according to the invention can, in particular, be uploaded to a network, for example, an Internet-type network.

[0041] Alternatively, the recording medium may be an integrated circuit in which the program is incorporated, the circuit being adapted to execute or to be used in the execution of the aforementioned communication process.

[0042] According to one embodiment, the present technique is implemented using software and / or hardware components. In this context, the term "device" or "module" may refer in this document to a software component, a hardware component, or a set of hardware and software components. Brief description of the drawings

[0043] Other features and advantages will become apparent upon reading particular embodiments of the invention, given by way of illustrative and non-limiting examples, and the accompanying drawings, among which:

[0044] [Fig-1] Fig. 1 represents an architecture in which the communication method, according to a particular embodiment of the invention,

[0045] [Fig.2] The [Fig.2] represents a computer device according to a particular embodiment of the invention, as implemented in the architecture of the [Fig.1],

[0046] [Fig.3A] [Fig.3A] represents the main actions implemented in the communication process, according to a particular embodiment of the invention, as implemented in the architecture of [Fig.1],

[0047] [Fig.3B] Fig.3B represents the main actions implemented in the communication process, according to a particular embodiment of the invention, as implemented in the architecture of Fig.1.

[0048] [Fig.4] Figure [Fig.4] represents an example of a web page generated during the implementation of the communication method, according to a particular embodiment of the invention,

[0049] [Fig.5] Figure [Fig.5] represents an example of a web page generated during the implementation of the communication method, according to a particular embodiment of the invention,

[0050] [Fig.6] The [Fig.6] represents the main actions implemented during a data enrichment phase of the communication process, according to a particular embodiment of the invention, as implemented in the architecture of [Fig.1].

[0051] Detailed description of an embodiment of the invention

[0052] Fig. 1 represents an architecture in which a communication process is implemented, according to one embodiment of the invention.

[0053] Such an architecture comprises:

[0054] - a computer device DI comprising a knowledge base BC modeling data in the form of a knowledge graph (KG);

[0055] - a human-machine interface (HMI) configured to be activated by a user (UT) to communicate with the DI computer system.

[0056] The DI computer system may include, for example, a computer, a server, a platform, etc.

[0057] In [Fig. 1], the knowledge base BC is integrated into the computer device DI. Of course, such a knowledge base BC can be separate from the computer device DI, the latter then being configured to communicate with the knowledge base BC by any suitable means of communication.

[0058] The UI interface may include, for example, a text-based graphical interface or a sound sensor coupled with a speech recognition interface. Such an interface may belong to the computer device DI or be separate from it. The knowledge graph GC is, for example, of the Wikidata, DBpedia, Google Knowledge Graph, Microsoft Concept Graph, etc. type.

[0059] We will now describe, with reference to [Fig.2], the simplified structure of the DI computer device.

[0060] According to the invention, the DI computer device comprises:

[0061] - a COM communication module configured to receive generated requests using the user interface,

[0062] - a CMD command module configured to control the restoration of responses to generated queries,

[0063] - a GPR prompt generation module configured to generate a prompt in natural language

[0064] - an LNT natural language model configured to be queried from the prompt generated. Such a natural language model can be, for example, an n-grams model, a recurrent neural network (RNN), a large language model (LLM), etc. The natural language model (LNT) has been classically trained to accumulate knowledge.

[0065] According to the invention:

[0066] - the COM communication module is configured to receive, in particular, a query REQ1 generated using the UI interface, said query including information relating to an entity of the knowledge graph GC.

[0067] An entity can be, for example, the name of an object, a person, a company, etc.

[0068] - the CMD command module is configured to, among other things, control the rendering of a web page containing the information requested in the REQ1 query.

[0069] Also according to the invention:

[0070] - the COM communication module is configured to receive, in particular, a REQ2 query generated using the UI interface, the REQ2 query asking the less one missing or desirable property of said entity, among the information restored,

[0071] - the CMD command module is configured to, among other things, control the rendering of a web page containing a LP list of missing properties ranked by frequency of observation of these properties for other entities of the same type as said entity.

[0072] The entity information contained in the REQ1 query may include, in natural language, the entity name entered manually or spoken by the UT user via the UI interface. Alternatively, the REQ1 query may be written in a computer language, for example SQL (Structured Query Language), Python, etc.

[0073] According to the invention:

[0074] - The GPR prompt generation module is configured to generate automatically, that is, without user intervention, a prompt will appear asking for the value of at least one of the missing properties from the LP list that was restored using the CMD command module,

[0075] - the LNT natural language model is configured to be queried from this Prompt generated

[0076] - the CMD command module is specifically configured to control the rendering a web page containing a value V of said at least one missing property.

[0077] Optionally, according to the invention, the COM communication module is configured to receive, in response to the rendering of a web page containing an LP list of missing properties ranked by frequency of observation of these properties for other entities of the same type as said entity, a REQ3 request generated using the UI interface, said REQ3 request containing a threshold of frequency of observation of these properties in the knowledge base.

[0078] Optionally, according to the invention, the computer device DI may include an MST storage module in which a threshold TH of the observation frequency of the properties missing in the knowledge base BC is stored. Such an MST storage module being optional, it is represented by dashed lines in [Fig. 2].

[0079] According to the invention, the DI computer device may include an ADD addition module which is configured to add the value V of said at least one missing property to the knowledge graph GC. The ADD module being optional, it is represented by dashed lines in [Fig.2].

[0080] According to the invention, the COM communication module can be configured to, in particular, receive a REQ4 request asking for validation or non-validation of the value of said at least one missing property.

[0081] At initialization, the code instructions of the computer program PG are, for example, loaded into RAM (not shown) before being executed by the PROC processor. The PROC processor of the UTR processing unit implements, in particular, the following actions, within the framework of the communication process that will be described below, according to the instructions of the computer program PG:

[0082] - receive the REQ1 request including information relating to an entity of the knowledge graph,

[0083] - to order the rendering of a web page containing said information,

[0084] - receive the REQ2 request asking for at least one missing property of said entity, among the aforementioned information provided,

[0085] - command the rendering of a web page containing a list of properties missing properties, ranked by frequency of observation of these properties for other entities of the same type,

[0086] - query the LNT language model from the prompt generated in natural language, said prompt asking the language model what the value V is of at least one of the properties of the list,

[0087] - to order the rendering of a web page containing said value V,

[0088] - possibly add the value V of said at least one missing property to GC knowledge graph,

[0089] - possibly receive the REQ3 request containing a frequency threshold observation of missing properties in the knowledge base,

[0090] - optionally record the TH threshold of observation frequency of the properties missing from the BC knowledge base,

[0091] - possibly receive the REQ4 request asking for validation or non- validation of the value of said at least one missing property.

[0092] We now describe, in relation to [Fig.3A], together with Figures 1 and 2, the process of communication with the computer device DI, according to a first particular embodiment of the invention.

[0093] In an optional preliminary step SOI, the user UT configures the computer system DI by setting, for an entity ENT in the knowledge graph GC, searched by the user UT, a threshold TH for the frequency of observation of the missing properties of this entity in the knowledge base BC, for at least one other entity of the same type as this entity. To this end, using the IU interface, the user UT enters the threshold TH, for example 50%, or pronounces the threshold TH verbally.

[0094] During an optional preliminary step S02, the threshold TH is recorded in the MST memory of the DI computing device.

[0095] Since steps SOI and S02 are optional, they are represented by dotted lines on [Fig.3A].

[0096] During an Sla step, the user UT sends a REQ1 request to the knowledge graph GC, via the IU interface, said REQ1 request including information relating to the ENT entity of the knowledge graph GC. This request is received in Slb by the DI computer device, via its COM module.

[0097] The information contained in the REQ1 query may include one or more words. Such a query may be written in natural language or in a particular computer language, for example SQL (Structured Query Language), Python, etc.

[0098] In one embodiment, the query REQ1 includes the word "iPhone 6S", designating the ENT entity "iPhone 6S".

[0099] During a step S2, the CMD control module of the DI computing device commands the rendering of a PI web page containing information relating to the required ENT entity. In the example shown in [Fig. 4], the PI web page contains information relating to the entity "iPhone 6S," which contains a unique identifier within the knowledge graph GC, Q60903, in the example shown. Several knowledge triplets relate to this entity. A knowledge triplet is a set of three elements<sujet, propriété, objet> In the example of [Fig. 4], clPhone 6S (Q60903), processor, Apple A9> is a knowledge triplet linking a subject "iPhone 6S", a property "processor", and an object "Apple A9". Subsequently, two types of properties are distinguished:

[0100] - the properties of objects linking one entity to another through a property. For example, the "processor" property is an object property linking the "iPhone 6S" entity to the "Apple A9" entity, itself represented by a unique identifier in the GC knowledge graph.

[0101] - data properties linking an entity to a value through a property. For example, the "thickness" property is a data property that assigns the value 7.1 to the entity "iPhone 6S". Values ​​can be of different types: numeric, date, string, etc.

[0102] During a step S3a, the user UT sends a REQ2 request to the knowledge graph GC, via the IU interface, said REQ2 requesting at least one missing property of the entity ENT, among said information returned in S2. This request is received in S3b by the computer device DI, via its COM module.

[0103] In a manner known per se, the user UT activates a knowledge graph analysis tool which allows, for a given entity, the calculation of a completeness rate of the entity relative to entities of the same type (in the semantic type sense within the knowledge graph) and to identify the missing properties commonly observed for this type. The type of an entity here refers to a knowledge triplet that allows the entity to be "classified" into one or more semantic categories via a specific typing property, for example, "nature of the element" in [Fig. 4]. The "nature of the element" property in [Fig. 4] links the entity "iPhone 6S" to the type "item". The entity "iPhone 6S" could also have been typed with the entity "Mobile Phone", for example.

[0104] An example of such a tool is, for example, the RECOIN extension (https: / / www.wikidata.org / wiki / Wikidata:Recoin) of Wikidata, which allows, using calculations of the frequency of occurrence of properties, the listing of desirable or missing properties for a given entity.

[0105] Another example of such a tool is the Wiki2Prop tool described in the paper "Wiki2Prop: A Multimodal Approach for Predicting Wikidata Properties from Wikipedia," WWW '21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, which allows for the suggestion of new properties for an entity based on its associated Wikipedia page. As described in this paper, the identification of desirable properties for an entity is carried out using a knowledge graph analysis. Given an entity and its type (encoded in the knowledge graph), the tool calculates the frequencies of properties instantiated and observed on entities of the same type in the knowledge graph. Based on this calculation, the tool outputs a completeness rate for the entity compared to entities of the same type, as well as a list of properties ranked by frequency of observation on other entities of the same type.

[0106] During a step S4, the CMD control module of the DI computer device commands the rendering of a Web page P2 containing a list of missing properties ranked by frequency of observation of these properties for other entities of the same type, ranging from 60% to 10% in the example shown.

[0107] An example of such a P2 web page is shown in [Fig. 5], in the case of the entity "iPhone 6S". In the example shown, a LP list of ten missing properties is generated, each property in this list being associated with an ID in the knowledge graph and an estimated observation frequency as a percentage.

[0108] Of course, this example is not exhaustive. In another example not shown, depending on the entity to be searched for in the GC knowledge graph, only one property could be generated in association with its ID identification and its observation frequency.

[0109] During an S5 step, the GPR prompt generation module automatically generates a PRP prompt requesting the value of at least one of the properties from the list that was rendered in the P2 web page. Such a PRP prompt is, for example, a natural language phrase such as: "What is the value of the DESIRED PROPERTY property for the ENT entity TO BE COMPLETED? Return only the value found." Further contextual information can be added to the PRP prompt as "context" to guide the data generation by the LNT language model. Such contextual information can, for example, be added using a well-known method called "prompt engineering." This method aims to enrich and structure the prompt to increase the accuracy and quality of the results provided by the LNT language model.In the example shown in Figures 4 and 5, it could be considered, for instance, to provide more context to the LNT language model by inserting fragments of text documents about the topic "iPhone 6S" into the PRP prompt as context. It could also be considered, for example, to manually add constraints to the prompt based on the user's (UT) knowledge of the knowledge graph (GC). For example, in the case of the property "energy storage capacity," the UT can use their prior knowledge of this particular property (knowledge from the knowledge graph). If, for example, the target "has milliampere-hour (mAh) as its unit" for the property "energy storage capacity" has not been encoded in the knowledge graph (GC), the UT could, for example, specify in the PRP prompt that a response with milliampere-hour (mAh) as its unit is expected.

[0110] During an S6 step, the PRP prompt is submitted to the LNT language model which, during an S7 step, generates a corresponding value V for each of the properties in the LP list, 10 values ​​in the example shown in [Fig. 5]. Depending on the type of missing properties, the generated value V relates to a data property or a value property.

[0111] When the generated value relates to a data property, no special post-processing is required other than formatting to conform to the format expected by the GC knowledge graph (e.g., a specific date format). For example, in the case of the property "energy storage capacity", the LNT language model can generate the value V "1715 (mAh)" without requiring any further processing to be added subsequently to the GC knowledge graph.

[0112] When the generated value relates to an object property, a well-known entity linking step is implemented to transform the string representing an ENT entity into an entity identifier known from the knowledge base BC. For example, if the prompt asks for a value V for the property "developed by" shown in [Fig. 5], the LNT language model might respond with the string "Apple". This string is unusable as is because it is ambiguous. It is impossible to know whether this string refers to a fruit, a company name, or something else. Furthermore, this string does not correspond to an entity identifier in the knowledge graph GC. This justifies the need for a disambiguation step, in other words, choosing the correct meaning of the entity based on the context, and entity linking, that is, finding the identifier, in the knowledge graph GC, of ​​the entity corresponding to the text "Apple".

[0113] During an S8 step, the CMD control module of the DI computing device commands the rendering of a P3 web page containing the value V of at least one of the missing properties from the LP list, for example, the one with the highest observation frequency in the LP list. Alternatively, in the example in [Fig. 5], the P3 web page can contain the ten V values ​​associated with the ten missing properties. According to another non-exhaustive example, ten P3 web pages, each containing a V value of one of the ten missing properties, can be rendered successively in S8.

[0114] According to one embodiment of the invention, in the case where the steps SOla, SOlb, S02 of setting a threshold TH of the observation frequency have been implemented, the PRP prompt generated in S5 only asks for the values ​​of the missing properties for which the observation frequency is greater than or equal to or strictly greater than the threshold TH which, in the aforementioned example, is 50%.

[0115] With reference to [Fig. 5], only the missing property P1008 "Energy Storage Capacity" exceeds this threshold TH. The PRP prompt generated in S5 is therefore unique and includes, for example, the phrase in natural language of the type: "What is the value of the property "Energy Storage Capacity" for the entity "iPhone 6S"? Returns only the value found." The PRP prompt is then submitted in S6 to the LNT language model, which generates in S7 the value V "1715 (mAh)".

[0116] With reference to [Fig. 6], we now describe a phase of enriching the knowledge graph GC, according to one embodiment of the invention. Such a phase can be implemented after step S8 of restoring the value V, as represented in [Fig. 3A].

[0117] This enrichment phase includes:

[0118] - an STI step of validation or non-validation by the UT user, of the value V restored in S8, using the aforementioned UI interface,

[0119] - in the case where the value V is validated (O on [Fig.6]), an ST2 addition step in the knowledge graph GC, by the ADD module of the DI computer device, of the value V, in association with the entity ENT for which the user UT requested information at step Sla of the [Fig.3A].

[0120] If the value V is not validated (N in [Fig. 6]), the communication process is terminated. The knowledge graph GC will therefore not be enriched with the value V for the entity ENT.

[0121] We now describe, in relation to [Fig.3B], together with Figures 1 and 2, the process of communication with the computer device DI, according to a second particular embodiment of the invention.

[0122] This second embodiment differs from the first embodiment in that it does not include the optional steps of setting the threshold TH SOI a, SOlb, S02.

[0123] This second embodiment provides another optional way of generating a TH threshold for the observation frequency, as will be described below. Unlike the embodiment of [Fig. 3A] where the TH threshold is determined prior to the implementation of the communication method, in this second embodiment, the TH threshold can be determined dynamically, on the fly, during the communication method.

[0124] The communication method, according to the second embodiment, comprises steps S'la to S'4 identical to steps Sla to S4 of [Fig. 3A]. For this reason, they will not be described again.

[0125] At the end of step S'4, during an optional step S'5a, the user UT sends a REQ4 request to the computer device DI, via the IU interface, said REQ4 request containing the threshold TH. This request is received in S'5b by the computer device DI, via its COM module.

[0126] The following steps S'6 to S'9 are identical to steps S5 to S8 of [Fig.3A]. For this reason, they will not be described again.

[0127] Following step S'9, the enrichment phase shown in [Fig.6] can be implemented.

[0128] The communication process described above makes it possible, in particular, to limit the intervention of human contributors in populating a knowledge graph by integrating a generative AI (Artificial Intelligence) module into the construction chain, capable of generating new knowledge. Users can thus rely, through a suitable application, on generative artificial intelligence technology to propose relevant content to enrich entities in the knowledge graph. This process also allows for the sparing use of the generative AI module by limiting inference operations, which represent a significant cost, both financially and otherwise. than environmental. The invention is applicable to any field requiring the construction of a knowledge graph.

Claims

Demands

1. A method of communicating with a computer device (CD) comprising a knowledge base (KB) modeling data in the form of a knowledge graph (KG), said method comprising the following, at the level of said device: - receiving (S1b; S'1b) a first request (REQ1) comprising information relating to an entity (ENT) of the knowledge graph, - requesting (S2; S'2) the rendering of a web page (P1) containing said information, - receiving (S3b; S'3b) a second request (REQ2) requesting at least one missing property of said entity, among said rendered information, - requesting (S4; S'4) the rendering of a web page (P2) containing a list (LP) of missing properties ranked by frequency of observation of these properties for other entities of the same type, - querying (S5-S7;S'6-S'8) a language model (LNT), from a prompt (PRP) generated in natural language by said device, said prompt asking the language model what the value (V) of at least one of the properties of the list is, - command (S8 ; S'9) the rendering of a Web page (P3) containing said value.;

2. A communication method according to claim 1, wherein said prompt is generated for a number of properties of said list which is determined with respect to a threshold (TH) of observation frequency of these properties in the knowledge base, for at least one other entity of the same type as said entity.

3. Communication method according to claim 2, wherein said observation frequency threshold (TH) is defined (S01a-S02) prior to the implementation of the communication method or is contained in a third request (REQ3) received (S'5b) by said device, in response to the rendering (S'4) of the web page containing the list of missing properties.

4. A communication method according to any one of claims 1 to 3, comprising the following: - receive (STI) a selection of a validation or non-validation of said value (V) contained in the web page rendered using a human-machine interface, - add (ST2) said value to the knowledge graph, in association with said entity, if validation of the value is requested.

5. A communication method according to any one of claims 1 to 4, wherein said value (V) is related to a data property or an object property.

6. A computer system (CS) comprising a knowledge base modeling data in the form of a knowledge graph, the system being characterized in that it is configured to implement: - receiving a first request including information relating to an entity in the knowledge graph, - a command to render a web page containing said information, - receiving a second request requesting at least one missing property of said entity, from among said returned information, - a command to render a web page containing a list of missing properties ranked by frequency of observation of these properties for other entities of the same type, - querying a language model, from a prompt generated in natural language by said system, said prompt asking the language model what the value of at least one of the properties in the list is.- a command to display a web page containing said value.

7. A computer program comprising program code instructions for implementing the communication method according to any one of claims 1 to 5, when executed on a computer.

8. Computer-readable information carrier, and containing instructions for a computer program according to claim 7.

Images