A method for a combined prompt providing entity, a method for a service provider, a method for an additional prompt providing entity, a combined prompt providing entity, a service provider, and an additional prompt providing entity

Abstract

Embodiments of the invention relate to creation of a combined prompt (930) to be provided to a generative artificial intelligence model (550). The combined prompt is generated based on a user prompt (910) provided by a user entity (700), and based on at least one additional prompt (920, 920', 920''), if one or more criteria (921, 921', 921'') associated with the at least one additional prompt is met by the user prompt. The at least one additional prompt is associated with one or more specific content characteristics. The combined prompt is then provided to a generative artificial intelligence model configured to generate a combination (940) of content generated based on the user prompt and one or more specific content characteristics generated based on the at least one additional prompt. The generated combination is then provided to the user entity. Some embodiments also relate to corresponding methods and a computer program.

Description

[0001] A METHOD FOR A COMBINED PROMPT PROVIDING ENTITY, A METHOD FOR A SERVICE PROVIDER, A METHOD FOR AN ADDITIONAL PROMPT PROVIDING ENTITY, A COMBINED PROMPT PROVIDING ENTITY, A SERVICE PROVIDER, AND AN ADDITIONAL PROMPT PROVIDING ENTITY

[0002] TECHNICAL FIELD

[0003] Embodiments of the invention relate to a method for a combined prompt providing entity of a service provider, to a method for a service provider comprising the combined prompt providing entity, and to method for an additional prompt providing entity.

[0004] Furthermore, embodiments of the invention also relate to a corresponding combined prompt providing entity of a service provider, a corresponding service provider comprising the combined prompt providing entity, a corresponding an additional prompt providing entity, and a computer program.

[0005] BACKGROUND

[0006] In recent years, generative artificial intelligence (Al) has emerged in form of large artificial intelligence models being used to generate content. Such generated content may comprise text from text content, for example as a service by ChatGPT from the service provider OpenAI.com. The content may also comprise images from text content, for example as a service by Stable Diffusion from the service provider Stability. ai. The content may also comprise video from text content, for example as a service by Sora from the service provider OpenAI.com. As understood by a skilled person, essentially any generative artificial intelligence service from any service provider may be added to this list as further examples.

[0007] These services are typically hosted in the service provider’s own cloud and / or infrastructure functions. Access to these services is usually provided through a web browser interface, a mobile application and / or an application programming interface. Typically, the services are provided free of charge. Alternatively, for a better quality of service, the user may pay for the service through a subscription or by paying a fee based on usage of the service.

[0008] Also, further expected developments indicate that these generative artificial intelligence approaches could at least partially replace the currently used internet search engines.

[0009] SUMMARY

[0010] The service providers are today unable to properly influence the content being generated by a generative artificial intelligence model. A user prompt provided by a user entity is simply input into the generative artificial intelligence model, and the content being generated by the generative artificial intelligence model based on this user prompt is output to the user entity.

[0011] It is therefore a risk that the generated content being output may comprise unsuitable material. For example, the generated content may comprise material being very unsuitable for being presented to children, such as violent or pornographic content, may comprise racist material, or may comprise misleading or false information.

[0012] Also, the service providers are today also unable to properly customize the content being generated by a generative artificial intelligence model, by incorporating suitable information to the content. It is therefore a risk that the user entity is not provided with information that may be of useful for a user of the user device.

[0013] An objective of embodiments of the invention is to provide a solution which mitigates or solves the drawbacks and problems of conventional solutions. Another objective of embodiments of the invention is to provide a solution which makes it possible for a service provider to influence and / or customize the content being generated and output by a generative artificial intelligence model.

[0014] The above and further objectives are solved by the subject matter of the independent claims. Further embodiments of the invention can be found in the dependent claims.

[0015] According to a first aspect of the invention, the above mentioned and other objectives are achieved with a method for a combined prompt providing entity of a service provider, the method comprising: obtaining a user prompt from a user entity; obtaining, from an additional prompt providing entity, at least one additional prompt associated with one or more specific content characteristics, and one or more criteria for when the one or more specific content characteristics should be generated; creating a combined prompt based on the user prompt and the at least one additional prompt if the one or more criteria is met by the user prompt; and providing the combined prompt to a generative artificial intelligence model of the service provider.

[0016] An advantage of the method for the combined prompt providing entity according to the first aspect is that a combined prompt is created and provided to a generative artificial intelligence model if the criteria associated with the at least one additional prompt is met by the user prompt. Hereby, the one or more specific content characteristics associated with the at least one additional prompt may be used for influencing and / or customizing the content being generated by the generative artificial intelligence model.

[0017] Thus, the generated content may here be influenced and / or customized by the combined prompt providing entity of the service provider, based on the at least one additional prompt, such that the service provider is able to control the content being generated and output to the user entity.

[0018] Hereby, it is possible for the service provider to prevent that the generated content being output comprises unsuitable material.

[0019] It is also possible for the service provider to customize the content being generated by a generative artificial intelligence model, and to add / incorporate suitable information to the content.

[0020] The service provider may thus for example, by incorporating the one or more specific content characteristics into the generated content, add recommendations in the generated content, such as in generated text content. The recommendations are then generated and included in the text in a natural way by the generative artificial intelligence model. The recommendations may be in form of advertisement indications being seamlessly incorporated in the generated content being provided to the user entity. The generative artificial intelligence model may thereafter be prompted to direct the user towards an advertiser or product provider designed to provide the recommendations and / or advertisement indications. The service provider may then be financially compensated by the advertiser or product provider for incorporating the recommendations in the content.

[0021] The service provider may also, by incorporating the one or more specific content characteristics into the generated content, comprising for example image, video and / or audio content, seamlessly incorporate product placement indications into the generated content. The generated content, including the product placement indications is then provided to the user entity. The service provider may here be financially compensated by an advertiser or product provider providing the product placement indications for incorporating the product placement indications in the content.

[0022] Thus, a controlled high quality and accuracy of the generated content is ensured both for the user and for the advertiser or product provider. The generated content will, by use of the presented combined prompt providing entity, fulfil the demands of the advertiser or product provider, since the generated content is a combination of content generated based on the user prompt and the one or more specific content characteristics generated based on the at least one additional prompt, when the criteria defined by the advertiser or product provider is met by the user prompt from the user entity.

[0023] In an implementation form of a method according to the first aspect, the method further comprises: obtaining, from the additional prompt providing entity, two or more additional prompts, and one or more criteria and an incentive associated with each of the two or more additional prompts; evaluating each of the two or more additional prompts based on if its associated one or more criteria are met by the user prompt and on its associated incentive; and selecting, based on the evaluation, at least one of the two or more additional prompts; and creating, based on the selection, the combined prompt based on the user prompt and the at least one additional prompt.

[0024] An advantage with this implementation form is that an advertiser or a product provider may financially compensate the service provider for generating content incorporating the one or more specific content characteristics generated based on the at least one additional prompt. If the criteria associated with two or more additional prompts are met by the user entity, the two or more additional prompts are evaluated based also on their individual associated incentives. Thus, the advertiser or product provider offering the most attractive incentive, e.g. the highest monetary compensation, may hereby be able to have the one or more specific content characteristics generated based on its at least one additional prompt incorporated in the generated content. Also, the service provider may hereby be compensated by the advertiser or a product provider for including one or more specific content characteristics generated based its at least one additional prompt in the generated content.

[0025] In an implementation form of a method according to the first aspect, the combined prompt is configured to produce a combination of: content generated by the generative artificial intelligence model based on the user prompt; and the one or more specific content characteristics generated by the generative artificial intelligence model based on the at least one additional prompt.

[0026] An advantage with this implementation form is that the generated content is generated based on both the user prompt and is also tailored / customized based on the additional prompt, such that one or more specific content characteristics specifically designed for matching a certain user prompt are incorporated into the generated content.

[0027] In an implementation form of a method according to the first aspect, the user prompt comprises one or more in the group of: text information; image information; video information; and audio information.

[0028] An advantage with this implementation form is that essentially any type of user prompt may be utilized by the herein presented combined prompt providing entity as input from a user entity . This makes the herein presented generation of customized content flexible and applicable in various technical implementations.

[0029] In an implementation form of a method according to the first aspect, the one or more criteria comprise one or more in the group of: one or more trigger words; one or more trigger images; one or more trigger video sequences; and one or more trigger audio sequences.

[0030] An advantage with this implementation form is that the criteria may be chosen such that they are useful for essentially any type of user prompt being input by a user of a user entity. This makes the herein presented generation of customized content flexible and applicable in various technical implementations.

[0031] In an implementation form of a method according to the first aspect, the user entity is one in the group of: a mobile phone; a mobile tablet; a laptop; and a stationary computer. An advantage with this implementation form is that the user prompt may be provided from, and the generated combined content may be provided to, various types of user entities, which makes the herein presented generation of customized combined content applicable in many implementations.

[0032] In an implementation form of a method according to the first aspect, the one or more specific content characteristics comprises one or more in the group of: at least one limitation to be applied to the content generated by the generative artificial intelligence model based on the user prompt; at least one advertisement indication; and at least one product placement indication.

[0033] An advantage with this implementation form is that the generated content may here be influenced and / or customized by the combined prompt providing entity of the service provider, such that the service provider is able to control the content being generated and output to the user entity. It is thus possible for the service provider to prevent that the generated content being output comprises unsuitable material, such as for example violent or pornographic material, or material otherwise unsuitable for children.

[0034] It is also possible for the service provider to customize the content being generated by a generative artificial intelligence model, by for example adding recommendations in the generated content. The recommendations may then be generated and included in the text in a natural way, for example in form of advertisement indications being seamlessly incorporated in the generated content. The user of the user entity may thereby be guided to prompt the generative artificial intelligence model to be directed towards an advertiser or product provider designed for providing the recommendations and / or advertisement indications. The service provider may then be financially compensated by the advertiser or product provider in order to have the advertisement indications incorporated into the generated content.

[0035] Also, by incorporating the one or more specific content characteristics into generated content comprising for example image, video and / or audio content, the service provider may seamlessly incorporate product placement into the generated content being provided to the user entity. The service provider may here be financially compensated by an advertiser or product provider in order to get the product placement indications incorporated into the generated content.

[0036] According to a second aspect of the invention, the above mentioned and other objectives are achieved with a method for a service provider, the method comprising: providing, according to a herein described method for a combined prompt providing entity, a combined prompt to a generative artificial intelligence model of the service provider; generating, by usage of the generative artificial intelligence model, a combination of content generated based on the user prompt and the one or more specific content characteristics generated based on the at least one additional prompt; and providing the generated combination to the user entity.

[0037] An advantage of the method for the service provider according to the second aspect is that the generated content being provided to the user entity may here be influenced and / or customized by the combined prompt providing entity of the service provider, such that the service provider is able to control the content being generated and output to the user entity.

[0038] The service provider may hereby prevent that the generated content being output by the generative artificial intelligence model comprises unsuitable material. The service provider may also customize the content being generated, for example by incorporating suitable information to the content.

[0039] According to a third aspect of the invention, the above mentioned and other objectives are achieved with a method for an additional prompt providing entity, the method comprising: determining at least one additional prompt associated with one or more specific content characteristics; determining one or more criteria for when the one or more specific content characteristics should be generated; and providing the at least one additional prompt and the one or more criteria to a combined prompt providing entity.

[0040] An advantage of the method for the additional prompt providing entity according to the third aspect is that one or more specific content characteristics associated with the at least one additional prompt may be used for influencing and / or customizing the content being generated by the generative artificial intelligence model, such that the generated content is specifically customized to a user prompt provided by a user entity if the defined criteria is met by the user prompt. Thus, a seamless adaption of the generated content is provided, which is based on the user prompt being input by a user of the user entity. The generated content is, in other words specifically customized based on the user prompt being input by the user.

[0041] In an implementation form of the method according to the third aspect, the additional prompt providing entity being further configured to: determining two or more additional prompts, wherein each of the two or more additional prompts is associated with one or more specific content characteristics; determining one or more criteria for when the one or more specific content characteristics associated with each of the two or more additional prompts should be generated; determining for each of the two or more additional prompts an incentive for the combined prompt providing entity to include the additional prompt in a combined prompt; and providing the two or more additional prompts, and the one or more criteria and the incentive associated with each of the two or more additional prompts to a combined prompt providing entity.

[0042] An advantage with this implementation form is that an advertiser or a product provider may financially compensate the service provider for generating content incorporating the one or more specific content characteristics generated based on the at least one additional prompt. If the criteria associated with two or more additional prompts are met by the user entity, the two or more additional prompts are evaluated based also on their individual associated incentives. The advertiser or product provider offering the most attractive incentive, e.g. the highest fee or other compensation, will get its one or more specific content characteristics generated based on the associated at least one additional prompt incorporated in the generated content. This also makes it possible for the service provider to be compensated by the advertiser or a product provider for including one or more specific content characteristics generated based on its at least one additional prompt in the generated content.

[0043] According to a fourth aspect of the invention, the above mentioned and other objectives are achieved with a combined prompt providing entity of a service provider, wherein the combined prompt providing entity comprises a processor and a memory; the memory is configured to store instructions; and the processor is configured to read the instructions to perform a herein described method for the combined prompt providing entity.

[0044] The combined prompt providing entity according to the fourth aspect can be extended into implementation forms corresponding to the implementation forms of the method for the combined prompt providing entity according to the first aspect. Hence, an implementation form of the combined prompt providing entity comprises the feature(s) of the corresponding implementation form of the method for the combined prompt providing entity.

[0045] The advantages of the combined prompt providing entity according to the fourth aspect are the same as those for the corresponding implementation forms of the method for the combined prompt providing entity according to the first aspect.

[0046] According to a fifth aspect of the invention, the above mentioned and other objectives are achieved with a service provider, wherein the service provider comprises a processor and a memory; the memory is configured to store instructions; and the processor is configured to read the instructions to perform a herein described method for the service provider. The service provider according to the fifth aspect can be extended into implementation forms corresponding to the implementation forms of the method for a service provider according to the second aspect. Hence, an implementation form of the service provider comprises the feature(s) of the corresponding implementation form of the method for a service provider.

[0047] The advantages of the service provider according to the fifth aspect are the same as those for the corresponding implementation forms of the method for the service provider according to the second aspect.

[0048] According to a sixth aspect of the invention, the above mentioned and other objectives are achieved with an additional prompt providing entity, wherein the additional prompt providing entity comprises a processor and a memory; the memory is configured to store instructions; and the processor is configured to read the instructions to perform a herein described method for an additional prompt providing entity.

[0049] The additional prompt providing entity according to the sixth aspect can be extended into implementation forms corresponding to the implementation forms of the method for additional prompt providing entity according to the third aspect. Hence, an implementation form of the additional prompt providing entity comprises the feature(s) of the corresponding implementation form of the method for an additional prompt providing entity.

[0050] The advantages of the additional prompt providing entity according to the sixth aspect are the same as those for the corresponding implementation forms of the method for the additional prompt providing entity according to the third aspect.

[0051] Embodiments of the invention also relate to a computer program, characterized in program code, which when run by at least one processor causes the at least one processor to execute any method according to embodiments of the invention. Further, embodiments of the invention also relate to a computer program product comprising a computer readable medium and the mentioned computer program, wherein the computer program is included in the computer readable medium, and may comprises one or more from the group of: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), flash memory, electrically erasable PROM (EEPROM), hard disk drive, etc.

[0052] Further applications and advantages of embodiments of the invention will be apparent from the following detailed description.

[0053] BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The appended drawings are intended to clarify and explain different embodiments of the invention, in which:

[0055] - Fig. 1 shows a combined prompt providing entity according to an embodiment of the invention;

[0056] - Fig. 2 shows a flow chart of a method for a combined prompt providing entity according to an embodiment of the invention;

[0057] - Fig. 3 shows a service provider according to an embodiment of the invention;

[0058] - Fig. 4 shows a flow chart of a method for a service provider according to an embodiment of the invention;

[0059] - Fig. 5 shows an additional prompt providing entity according to an embodiment of the invention;

[0060] - Fig. 6 shows a flow chart of a method for an additional prompt providing entity according to an embodiment of the invention;

[0061] - Fig. 7 shows a communication system according to an embodiment of the invention;

[0062] - Fig. 8 shows a flow chart of some steps of the herein presented methods according to some embodiments of the invention; and

[0063] - Fig. 9 shows a signaling diagram for the communication system. DETAILED DESCRIPTION

[0064] Fig. 1 shows a combined prompt providing entity 100 of a service provider 500 according to an embodiment of the invention. In the embodiment shown in Fig. 1, the combined prompt providing entity 100 comprises a processor 102, a transceiver 104 and a memory 106. The processor 102 is coupled to the transceiver 104 and the memory 106 by communication means 108 known in the art. The combined prompt providing entity 100 may further comprise communication means, such as e.g. a wired communication interface coupled to the transceiver 104, for wired communication. The combined prompt providing entity 100 may also comprise communication means, such as e.g. an antenna or antenna array coupled to the transceiver 104, for wireless communication. This means that the combined prompt providing entity 100 is configured for wired and / or wireless communications in a communication system.

[0065] The processor 102 may be referred to as one or more general-purpose central processing units (CPUs), one or more digital signal processors (DSPs), one or more application-specific integrated circuits (ASICs), one or more field programmable gate arrays (FPGAs), one or more programmable logic devices, one or more discrete gates, one or more transistor logic devices, one or more discrete hardware components, or one or more chipsets. The memory 106 may be a read-only memory, a random access memory (RAM), or a non-volatile RAM (NVRAM). The transceiver 104 may be a transceiver circuit, a power controller, or an interface providing capability to communicate with other communication modules or communication devices. The transceiver 104, memory 106 and / or processor 102 may be implemented in separate chipsets or may be implemented in a common chipset.

[0066] That the combined prompt providing entity 100 is configured to perform certain actions can in this disclosure be understood to mean that the combined prompt providing entity 100 comprises suitable means, such as e.g., the processor 102 and the transceiver 104, configured to perform the actions.

[0067] According to embodiments of the invention the combined prompt providing entity 100 of the service provider 500 is configured to obtain a user prompt 910 from a user entity 700.

[0068] The combined prompt providing entity 100 further is configured to obtain, from an additional prompt providing entity 300, at least one additional prompt 920, 920’, 920” associated with one or more specific content characteristics, and one or more criteria 921 , 921 ’, 921 ” for when the one or more specific content characteristics should be generated.

[0069] The combined prompt providing entity 100 is further configured to create a combined prompt 930 based on the user prompt 910 and the at least one additional prompt 920, 920’, 920” if the one or more criteria 921 , 921 ’ , 921 ” is met by the user prompt 910.

[0070] The combined prompt providing entity 100 further is configured to provide the combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500.

[0071] Furthermore, according to an embodiment of the invention, the combined prompt providing entity 100 comprises a processor and a memory having computer readable instructions stored thereon which, when executed by the processor, cause the processor to: obtain a user prompt 910 from a user entity 700; obtain, from an additional prompt providing entity 300, at least one additional prompt 920, 920’, 920” associated with one or more specific content characteristics, and one or more criteria 921, 921’, 921” for when the one or more specific content characteristics should be generated; create a combined prompt 930 based on the user prompt 910 and the at least one additional prompt 920, 920’, 920” iftheoneor more criteria 921, 921’, 921” is met by the user prompt 910; and provide the combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500. Fig. 2 shows a flow chart of a corresponding method 200 which may be executed in a combined prompt providing entity 100, such as the one shown in Fig. 1. The method 200 comprises a step 202 of obtaining a user prompt 910 from a user entity 700.

[0072] The method further comprises a step 204 of obtaining, from an additional prompt providing entity 300, at least one additional prompt 920, 920’, 920” associated with one or more specific content characteristics, and one or more criteria 921, 921’, 921” for when one or more specific content characteristics should be generated.

[0073] The method further comprises a step 206 of creating a combined prompt 930 based on the user prompt 910 and the at least one additional prompt 920, 920’, 920” if the one or more criteria 921, 921’, 921” is met by the user prompt 910.

[0074] The method further comprises a step 208 of providing the combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500.

[0075] Thus, the one or more criteria 921, 921’, 921” associated with the at least one additional prompt 920, 920’, 920” are provided to the combined prompt providing entity 100 by the additional prompt providing entity 300, as herein described. The one or more criteria 921 , 921’ , 921 ” are then stored in in the combined prompt providing entity 100 and are checked against the user prompts 910 being provided from the user entity 700. If at least one criterium associated with a specific additional prompt is met by a certain user prompt, that specific additional prompt is added to the user prompt meeting the at least one criterium, such that a combined prompt 930 is created, and provided to the generative artificial intelligence model 550.

[0076] As a non-limiting example, the user prompt 910 may include “Give me a list of five sci-fi books”. An additional prompt 920 may be “Propose book X” to be added if the associated criteria 921 “sci-fi books” is met by the user prompt 910, for example by a keyword match of “sci-fi books” in the user prompt 910. Since the criteria 920 “sci-fi books” is here met by the keyword match of the user prompt 910, a combined prompt 930 is created, which comprises “Give me a list of five sci-fi books and propose book X”. The generative artificial intelligence model 550 of the service provider 500 will then, based on the combined prompt 930 provided to it, generate a list of five books, where book X is at the top of the list.

[0077] According to an embodiment, the combined prompt providing entity 100 is configured to obtain two or more additional prompts 920’, 920”, and one or more criteria 921’, 921” and an incentive 922’, 922” associated with each of the two or more additional prompts 920”, 920” from the additional prompt providing entity 300. For example, a first additional prompt 920’, one or more first criteria 921’ associated with the first additional prompt 920’, and a first incentive 922’ associated with the first additional prompt 920 ’ are provided. Also, a second additional prompt 920 ’ ’ , one or more second criteria 921” associated with the second additional prompt 920”, and a second incentive 922” associated with the second additional prompt 920” are provided.

[0078] The combined prompt providing entity 100 is then configured to evaluate each of the two or more additional prompts 920’, 920” based on if its associated one or more criteria 921’, 921” are met by the user prompt 910 and on its associated incentive 922’, 922”.

[0079] For example, it is evaluated if the one or more first criteria 921’ associated with the first additional prompt 920’ is met by the user prompt 910. The first incentive 922’ associated with the first additional prompt 920’ is also evaluated. Further, it is evaluated if the one or more second criteria 921” associated with the second additional prompt 920 ’ ’ is met by the user prompt 910. The second incentive 922” associated with the second additional prompt 920” is also evaluated. The combined prompt providing entity 100 is further configured to select, based on the evaluation, at least one 920’ of the two or more additional prompts 920’, 920” to be included as a basis for the combined prompt 930.

[0080] For example, if the one or more first criteria 921’ associated with the first additional prompt 920’ is met by the user prompt 910, but the one or more second criteria 921” associated with the second additional prompt 920” is not met by the user prompt 910, then the first additional prompt 920’ is here selected to be included as a basis for the combined prompt 930.

[0081] The evaluation of the two or more additional prompts 920’, 920” may, according to an embodiment comprise utilization of an optimization algorithm. The optimization algorithm takes into account how well the one or more criteria 921’, 921” associated with each additional prompt 920’, 920” is met by the user prompt and / or how attractive the incentive 922’, 922” associated with these additional prompts 920’, 920” is for the combined prompt providing entity 100 and the service provider 500.

[0082] Thus, according to the optimization algorithm, the winning additional prompt to be included in the combined prompt 930 is an additional prompt which results in a maximal value for the optimization algorithm based on the matching of its criterium with the user prompt and on its associated incentive, for example:

[0083] W = max[match (criterium) + f( incentive)];

[0084] where

[0085] W is the winning additional prompt; and

[0086] f is an incentive transformation function.

[0087] F or example, if both of the one or more first criteria 921 ’ associated with the first additional prompt 920 ’ and the one or more second criteria 921” associated with the second additional prompt 920 ’ ’ are met equally well by the user prompt 910, then the evaluation of the first incentive 922’ associated with the first additional prompt 920’ and the second incentive 922” associated with the second additional prompt 920 ’ ’ decides which one of the first additional prompt 920 ’ and the second additional prompt 920” should be selected be included as a basis for the combined prompt 930. The first incentive 922’ and the second incentive 922 ’ ’ are thus compared with each other, and the first additional prompt 920 ’ or the second additional prompt 920 ’ ’ associated with the most attractive incentive is then selected. Thus, if the first incentive 922’ is determined more attractive / favourable for the combined prompt providing entity 100, e.g. by offering a higher fee, then the first additional prompt 920’ associated with the first incentive 922’ is selected.

[0088] The combined prompt providing entity 100 is further configured to create, based on the selection, the combined prompt 930 based on the user prompt 910 and the selected at least one additional prompt 920’.

[0089] According to an embodiment, the combined prompt 930 is configured to produce, in the generative artificial intelligence model 550, a combination of content generated by the generative artificial intelligence model 550 based on the user prompt 910, and the one or more specific content characteristics generated by the generative artificial intelligence model 550 based on the at least one additional prompt 920, 920’, 920”. Thus, the generated content may hereby be shaped / tailored / adjusted / amended / customized based on the one or more specific content characteristics.

[0090] According to an embodiment, the one or more specific content characteristics comprises at least one limitation to be applied to the content generated by the generative artificial intelligence model 550 based on the user prompt 910. For example, the at least one limitation may follow laws and / or regulations associated with the generated content. According to an embodiment, the one or more specific content characteristics comprises at least one advertisement indication. Thus, advertisements may hereby be incorporated into the generated content.

[0091] According to an embodiment, the one or more specific content characteristics comprises at least one product placement indication. Thus, a product placement, such as for example a trademark of some kind, may hereby be incorporated into the generated content.

[0092] According to various embodiments, the user prompt 910 provided by the user entity 700 comprises text information, image information, video information, and / or audio information.

[0093] Further, according to various embodiments, the one or more criteria 920, 920’, 920” comprise one or more trigger words, one or more trigger images one or more trigger video sequences, and / or one or more trigger audio sequences.

[0094] For example, if it is determined that one or more criteria trigger words correspond to, or is comprised in, text information of a user prompt 910, then it is determined that the one or more criteria 921, 921’, 921” is met by the user prompt 910. Correspondingly, if it is determined that one or more criteria trigger images correspond to, or is comprised in, image information of a user prompt 910, then it is determined that the one or more criteria 921, 921’, 921” is met by the user prompt 910. Also, if it is determined that one or more criteria trigger video sequences correspond to, or is comprised in, video information of a user prompt 910, then it is determined that the one or more criteria 921, 921’, 921” is met by the user prompt 910. Also, if it is determined that one or more criteria trigger audio sequences correspond to, or is comprised in, audio information of a user prompt 910, then it is determined that the one or more criteria 921, 921’, 921 ” is met by the user prompt 910.

[0095] According to various embodiments, the user entity 700 may be or comprise a mobile phone, a mobile tablet, a laptop and / or a stationary computer.

[0096] Fig. 3 shows a service provider 500. The service provider 500 comprises a herein disclosed combined prompt providing entity 100 configured to provide a combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500.

[0097] The service provider 500 further comprises the generative artificial intelligence model 550 configured to generate a combination 940 of content generated based on the user prompt 910 and the one or more specific content characteristics generated based on the at least one additional prompt 920, 920’, 920”, and to provide the generated combination 940 to the user entity 700.

[0098] Furthermore, according to an embodiment of the invention, the service provider 500 comprises a processor and a memory having computer readable instructions stored thereon which, when executed by the processor, cause the processor to: provide, as herein disclosed, a combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500; generate, by usage of the generative artificial intelligence model 550, a combination 940 of content generated based on the user prompt 910 and the one or more specific content characteristics generated based on the at least one additional prompt 930; and provide the generated combination 940 to the user entity 700.

[0099] Fig. 4 shows a flow chart of a corresponding method 400 which may be executed in a service provider 500. The method 400 comprises a step 402 of providing, as disclosed herein, a combined prompt 930 to a generative artificial intelligence model 550 of the service provider 500. The method 400 further comprises a step 404 of generating, by usage of the generative artificial intelligence model 550, a combination 940 of content generated based on the user prompt 910 and the one or more specific content characteristics generated based on the at least one additional prompt 920, 920’, 920”.

[0100] The method 400 further comprises a step 406 of providing the generated combination 940 to the user entity 700.

[0101] Fig. 5 shows an additional prompt providing entity 300 according to an embodiment of the invention. In the embodiment shown in Fig. 5, the additional prompt providing entity 300 comprises a processor 302, a transceiver 304 and a memory 306. The processor 302 is coupled to the transceiver 304 and the memory 306 by communication means 308 known in the art. The additional prompt providing entity 300 may further comprise communication means, such as e.g. a wired communication interface coupled to the transceiver 304 for wired communication and / or a wireless communication interface comprising e.g. an antenna or antenna array coupled to the transceiver 304 for wireless communication. This means that the additional prompt providing entity 300 is configured for wired and / or wireless communications in a communication system.

[0102] The processor 302 may be referred to as one or more general-purpose CPU, one or more DSPs, one or more ASICs, one or more FPGAs, one or more programmable logic devices, one or more discrete gates, one or more transistor logic devices, one or more discrete hardware components, one or more chipsets. The memory 306 may be a read-only memory, a RAM, or a NVRAM. The transceiver 304 may be a transceiver circuit, a power controller, or an interface providing capability to communicate with other communication modules or communication devices, such as network nodes and network servers. The transceiver 304, the memory 306 and / or the processor 302 may be implemented in separate chipsets or may be implemented in a common chipset.

[0103] That the additional prompt providing entity 300 is configured to perform certain actions can in this disclosure be understood to mean that the additional prompt providing entity 300 comprises suitable means, such as e.g., the processor 302 and the transceiver 304, configured to perform the actions.

[0104] Furthermore, according to an embodiment of the invention, the additional prompt providing entity 300 comprises a processor and a memory having computer readable instructions stored thereon which, when executed by the processor, cause the processor to: determine at least one additional prompt associated with one or more specific content characteristics; determine one or more criteria for when the one or more specific content characteristics should be generated; and provide the at least one additional prompt and the one or more criteria to a combined prompt providing entity.

[0105] Fig. 6 shows a flow chart of a corresponding method 600 which may be executed in an additional prompt providing entity 300, such as the one shown in Fig. 5. The method 600 comprises a step 602 of determining at least one additional prompt 920, 920’, 920” associated with one or more specific content characteristics.

[0106] The method 600 further comprises a step 604 of determining one or more criteria 921 , 921’ , 921 ” for when the one or more specific content characteristics should be generated.

[0107] The method 600 further comprises a step 606 of providing the at least one additional prompt 920, 920’, 920” and the one or more criteria 921 , 921’ , 921 ” to a combined prompt providing entity 100.

[0108] According to an embodiment, the additional prompt providing entity 300 is further configured to determine two or more additional prompts 920’, 920”, wherein each of the two or more additional prompts 920’, 920” is associated with one or more specific content characteristics. The additional prompt providing entity 300 is further configured to determine one or more criteria 921’, 921” for when the one or more specific content characteristics associated with each of the two or more additional prompts 920’, 920” should be generated.

[0109] The additional prompt providing entity 300 is further configured to determine, for each of the two or more additional prompts 920’, 920”, an incentive 922’, 922” for the combined prompt providing entity 100 to include the additional prompt 920’, 920” in a combined prompt 930

[0110] The additional prompt providing entity 300 is further configured to provide the two or more additional prompts 920’, 920”, and the one or more criteria 921’, 921” and the incentive 922’, 922” associated with each of the two or more additional prompts 920’, 920” to a combined prompt providing entity 100.

[0111] As a non-limiting example, a first additional prompt 920’ may be configured to tailor / shape / adjust / amend / customize the generated content to comprise information related to real and powerful vehicles if a first criterium of “fast car” is met by the user prompt 910. However, a second additional prompt 920” may be configured to tailor / shape / adjust / amend / customize the generated content to comprise information related to toy cars if a second criterium of “children’ s car” is met by the user prompt 910.

[0112] As another non-limiting example, a first additional prompt 920’ may be configured to tailor / shape / adjust / amend / customize the generated content to comprise information related to a first auto manufacturer if a first criterium 921’ of “car” is met by the user prompt 910. The first incentive 922’ for the combined prompt providing entity 100 to include the first additional prompt 920’ in a combined prompt 930 is set by the first auto manufacturer, e.g. as a first fee or financial compensation of some kind. Correspondingly, a second additional prompt 920” may be configured to tailor / shape / adjust / amend / customize the generated content to comprise information related to a second auto manufacturer if a second criterium 921” of “car” is met by the user prompt 910. The second incentive 922’ for the combined prompt providing entity 100 to include the second additional prompt 920” in a combined prompt 930 is set by the second auto manufacturer, e.g. as a second fee or financial compensation of some kind. Since the first criterium 921 ’ and the second criterium 921 ” are here both the same, i.e. “car” is present in the user prompt, then the first incentive 922’ and the second incentive 922’ become important. Thus, if the combined prompt providing entity 100 finds the first incentive 922’ more attractive, e.g. comprising a higher fee, than the second incentive 922”, then the first additional prompt 920’ will probably be chosen, such that the generated content is tailored / shaped / adjusted / amended / customized to comprise information related to a first auto manufacturer.

[0113] Fig. 7 shows a communication system 900 according to an embodiment of the invention. The communication system 900 according to the disclosed embodiment comprises a user entity / client device 700 and a network access node 750 configured to communicate and operate in the communication system 900. For simplicity, the shown communication system 900 only comprises one client device 100 and one network access node 750. However, the communication system 900 may comprise any number of client devices 700 and any number of network access nodes 750 without deviating from the scope of the invention. The network access node 750 may be connected to a network NW such as e.g., a core network over a communication interface. The communication system 900 may be a communication system according to the 3GPP standard such as e.g., a 5G system in which case the user entity 700 may be a user equipment (UE) and the network access node 750 may be a next generation node B (gNB) but the invention is not limited thereto. The communication system 900 further comprises a herein described service provider 500, comprising a herein described combined prompt providing entity 100, and an additional prompt providing entity 300. Fig. 8 shows a flow chart diagram for some steps performed in the herein presented embodiments for the combined prompt providing entity 100 and the service provider 500.

[0114] The combined prompt providing entity 100 obtains 202 a user prompt 910 from a user entity 700, and obtains 204 one or more criteria 921, 921’, 921” for when one or more specific content characteristics associated with at least one additional prompt 920, 920’, 920” should be generated from an additional prompt providing entity 300.

[0115] The combined prompt providing entity 100 then determines if the user prompt 910 meets the one or more criteria 921 , 921’ , 921”. If the user prompt 910 does not meet the one or more criteria 921 , 921’ , 921”, the user prompt 910 should be utilized as it is, and is thus provided to the generative artificial intelligence model 550.

[0116] However, if the user prompt 910 meets the one or more criteria 921 , 921’ , 921 ”, a combined prompt 930 is created 206 based on the user prompt 910 and the at least one additional prompt 920, 920’, 920”. The combined prompt 930 is then provided to the generative artificial intelligence model 550.

[0117] Fig. 9 shows a signaling diagram for the communication system 900 according to some embodiments.

[0118] In a first step I, the user entity 700 provides a user prompt 910 to the combined prompt providing entity 100.

[0119] In a second step II, the combined prompt providing entity 100 obtains the user prompt 910 from the user entity 700.

[0120] In a third step III, the additional prompt providing entity 300 determines at least one additional prompt 920, 920’, 920” associated with one or more specific content characteristics.

[0121] In a fourth step IV, the additional prompt providing entity 300 determines one or more criteria 921 , 921’ , 921 ” for when the one or more specific content characteristics should be generated.

[0122] In a fifth step V, the additional prompt providing entity 300 provides the at least one additional prompt 920, 920’, 920” and the one or more criteria 921, 921’, 921” to the combined prompt providing entity 100.

[0123] In a sixth step VI, the combined prompt providing entity 100 obtains the at least one additional prompt 920, 920’, 920” and the one or more criteria 921, 921’, 921” from the additional prompt providing entity 300.

[0124] In a seventh step VII, the combined prompt providing entity 100 creates a combined prompt 930 based on the user prompt 910 and the at least one additional prompt 920 , 920 ’ , 920 ” if the one or more criteria 921 , 921’ , 921 ” is met by the user prompt 910.

[0125] In an eighth step VIII, the combined prompt providing entity 100 provides the combined prompt 930 to a generative artificial intelligence model 550.

[0126] In a ninth step IX, the generative artificial intelligence model 550 obtains the combined prompt 930 from the combined prompt providing entity 100. In a tenth step X, the generative artificial intelligence model 550 generates a combination 940 of content generated based on the user prompt 910 and the one or more specific content characteristics based on the at least one additional prompt 920, 920’, 920”.

[0127] In an eleventh step XI, the generative artificial intelligence model 550 provides the generated combination 940 of content generated based on the user prompt 910 and the one or more specific content characteristics based on the at least one additional prompt 920, 920’, 920” to the user entity 700.

[0128] Further details related to embodiments of the invention will now be described in a 3GPP 5G context with reference to Figs. 1 to 7. Thus, 3GPP 5G terminology, definitions, expressions and system architecture will be used. Especially, the user entity 700 and the network access nodes 750 according to the invention may in these embodiments be configured to perform any of the described functions of a 3GPP user entity 700 and network access nodes 750, respectively. It may however be noted that embodiments of the invention are not limited thereto.

[0129] The user entity 700 herein may be denoted as a user device, a user equipment (UE), a mobile station, an internet of things (loT) device, a sensor device, a wireless terminal and / or a mobile terminal, and is enabled to communicate wirelessly in a wireless communication system, sometimes also referred to as a cellular radio system. The UEs may further be referred to as mobile telephones, cellular telephones, computer tablets or laptops with wireless capability. The UEs in this context may be, for example, portable, pocket-storable, hand-held, computer-comprised, or vehicle-mounted mobile devices, enabled to communicate voice and / or data, via a radio access network (RAN), with another communication entity, such as another receiver or a server. The UE may further be a station, which is any device that contains an IEEE 802.11 -conformant media access control (MAC) and physical layer (PHY) interface to the wireless medium (WM). The UE may be configured for communication in 3GPP related long term evolution (LEE), LTE-advanced, fifth generation (5G) wireless systems, such as new radio (NR), and their evolutions, as well as in IEEE related Wi-Fi, worldwide interoperability for micro wave access (WiMAX) and their evolutions.

[0130] The network access node 750 herein may also be denoted as a radio network access node, an access network access node, an access point (AP), or a base station (BS), e.g., a radio base station (RBS), which in some networks may be referred to as transmitter, “gNB”, “gNodeB”, “eNB”, “eNodeB”, “NodeB” or “B node”, depending on the standard, technology and terminology used. The radio network access nodes may be of different classes or types such as e.g., macro eNodeB, home eNodeB or pico base station, based on transmission power and thereby the cell size. The radio network access node may further be a station, which is any device that contains an IEEE 802.11 -conformant MAC and PHY interface to the WM. The radio network access node may be configured for communication in 3GPP related LTE, LTE-advanced, 5G wireless systems, such as NR and their evolutions, as well as in IEEE related Wi-Fi, WiMAX and their evolutions.

[0131] Furthermore, any method according to embodiments of the invention may be implemented in a computer program, having code means, which when run by processing means causes the processing means to execute the steps of the method. The computer program is included in a computer readable medium of a computer program product. The computer readable medium may comprise essentially any memory, such as previously mentioned a ROM, a PROM, an EPROM, a flash memory, an EEPROM, or a hard disk drive.

[0132] Moreover, it should be realized that the combined prompt providing entity 100, the service provider 500, and the additional prompt providing entity 300 comprise the necessary communication capabilities in the form of e.g., functions, means, units, elements, etc., for performing or implementing embodiments of the invention. Examples of other such means, units, elements and functions are: processors, memory, buffers, control logic, encoders, decoders, rate matchers, de-rate matchers, mapping units, multipliers, decision units, selecting units, switches, interleavers, de-interleavers, modulators, demodulators, inputs, outputs, antennas, amplifiers, receiver units, transmitter units, DSPs, TCM encoder, TCM decoder, power supply units, power feeders, communication interfaces, communication protocols, etc. which are suitably arranged together for performing the solution.

[0133] Therefore, the processor(s) of the combined prompt providing entity 100, the service provider 500, and the additional prompt providing entity 300 may comprise, e.g., one or more instances of a CPU, a processing unit, a processing circuit, a processor, an ASIC, a microprocessor, or other processing logic that may interpret and execute instructions. The expression “processor” may thus represent a processing circuitry comprising a plurality of processing circuits, such as e.g., any, some or all of the ones mentioned above. The processing circuitry may further perform data processing functions for inputting, outputting, and processing of data comprising data buffering and device control functions, such as call processing control, user interface control, or the like.

[0134] Finally, it should be understood that the invention is not limited to the embodiments described above, but also relates to and incorporates all embodiments within the scope of the appended independent claims.

Claims

CLAIMS1. A method (200) for a combined prompt providing entity (100) of a service provider (500), the method (200) comprising:obtaining (202) a user prompt (910) from a user entity (700);obtaining (204), from an additional prompt providing entity (300), at least one additional prompt (920, 920’, 920”) associated with one or more specific content characteristics, and one or more criteria (921 , 921’ , 921’ ’ ) for when one or more specific content characteristics should be generated;creating (206) a combined prompt (930) based on the user prompt (910) and the at least one additional prompt (920, 920’, 920”) if the one or more criteria (921, 921’, 921”) is met by the user prompt (910); andproviding (208) the combined prompt (930) to a generative artificial intelligence model (550) of the service provider (500).

2. The method (200) according to claim 1, further comprising:obtaining, from the additional prompt providing entity (300), two or more additional prompts (920’, 920”), and one or more criteria (921’, 921 ”) and an incentive (922’, 922”) associated with each of the two or more additional prompts (920’, 920”); evaluating each of the two or more additional prompts (920’, 920”) based on if its associated one or more criteria (921’, 921”) are met by the user prompt (910) and on its associated incentive (922’, 922”); andselecting, based on the evaluation, at least one (920’) of the two or more additional prompts (920’, 920”); and creating, based on the selection, the combined prompt (930) based on the user prompt (910) and the at least one additional prompt (920’).

3. The method (200) according to any one of claims 1-2, wherein the combined prompt (930) is configured to produce a combination of:content generated by the generative artificial intelligence model (550) based on the user prompt (910); and the one or more specific content characteristics generated by the generative artificial intelligence model (550) based on the at least one additional prompt (920, 920’, 920”).

4. The method (200) according to any one of claims 1-3, wherein the user prompt (910) comprises one or more in the group of:text information;image information;video information; oraudio information.

5. The method (200) according to any one of claims 1-4, wherein the one or more criteria (921, 921’, 921”) comprise one or more in the group of:one or more trigger words;one or more trigger images;one or more trigger video sequences; andone or more trigger audio sequences.

6. The method (200) according to any one of claims 1-5, wherein the user entity (700) is one in the group of:a mobile phone;a mobile tablet;a laptop; ora stationary computer.

7. The method (200) according to any one of claims 1-6, wherein the one or more specific content characteristics comprises one or more in the group of:at least one limitation to be applied to the content generated by the generative artificial intelligence model (550) based on the user prompt (910);at least one advertisement indication; andat least one product placement indication.

8. A method (400) for a service provider (500), the method (400) comprising:providing (402), according to a method of any one of claim 1 to 7 for a combined prompt providing entity (100), a combined prompt (930) to a generative artificial intelligence model (550) of the service provider (500);generating (404), by usage of the generative artificial intelligence model (550), a combination (940) of content generated based on the user prompt (910) and the one or more specific content characteristics generated based on the at least one additional prompt (920, 920’, 920”); andproviding (406) the generated combination (940) to the user entity (700).

9. A method (600) for an additional prompt providing entity (300), the method (600) comprising:determining (602) at least one additional prompt (920, 920’, 920”) associated with one or more specific content characteristics;determining (604) one or more criteria (921, 921’, 921”) for when the one or more specific content characteristics should be generated; andproviding (606) the at least one additional prompt (920, 920’, 920”) and the one or more criteria (921, 921’, 921”) to a combined prompt providing entity (100).

10. The method (600) according to claim 9, further comprising:determining two or more additional prompts (920’, 920”), wherein each of the two or more additional prompts (920’, 920”) is associated with one or more specific content characteristics;determining one or more criteria (921’, 921”) for when the one or more specific content characteristics associated with each of the two or more additional prompts (920’, 920”) should be generated;determining for each of the two or more additional prompts (920’, 920”) an incentive (922’, 922”) for the combined prompt providing entity (100) to include the additional prompt (920’, 920”) in a combined prompt (930); and providing the two or more additional prompts (920 ’ , 920 ” ), and the one or more criteria (921’ , 921 ” ) and the incentive (922’, 922”) associated with each of the two or more additional prompts (920’, 920”) to a combined prompt providing entity (100).

11. A combined prompt providing entity (100) of a service provider (500), whereinthe combined prompt providing entity (100) comprises a processor and a memory;the memory is configured to store instructions; andthe processor is configured to read the instructions to perform the method (400) according to any one of claims 1 to 7.

12. A service provider (500), whereinthe service provider (500) comprises a processor and a memory;the memory is configured to store instructions; andthe processor is configured to read the instructions to perform the method (400) according to claim 8.

13. An additional prompt providing entity (300), whereinthe additional prompt providing entity (300) comprises a processor and a memory;the memory is configured to store instructions; andthe processor is configured to read the instructions to perform the method (600) according to any one of claims 9 to 10.

14. A computer program with a program code for performing a method according to any one of claims 1-10 when the computer program runs on a computer.

Images