GB2629371A

GB2629371A - Help response based on one or more help parameters

Info

Publication number: GB2629371A
Application number: GB2306068.4A
Authority: GB
Inventors: William Walker Andrew; Ashton Derek Smith Alexei
Original assignee: Sony Interactive Entertainment Inc
Current assignee: Sony Interactive Entertainment Inc
Priority date: 2023-04-25
Filing date: 2023-04-25
Publication date: 2024-10-30
Also published as: GB202306068D0

Abstract

Help response generation apparatus 200 comprising communication circuitry 210 to receive a help request associated with a game, the help request indicating a goal to be achieved in the game, and processing circuitry 220 to generate, based on the help request, a help response, a hint, a tutorial, advice, or a guide. The processing circuitry is responsive to one or more help parameters associated with the help request to generate the help response in dependence on the one or more help parameters. The system may comprise a help response library and a look up mechanism for identifying relevant information in the library. Also disclosed is a method of providing a help response. Also disclosed is and entertainment system configured to provide help responses.

Description

HELP RESPONSE BASED ON ONE OR MORE HELP PARAMETERS

The present technique relates to the field of video games.

At times, while playing a video game on an entertainment system (such as a console or on a PC, for example), a player may make a request for help in achieving a particular goal.

For example, some games may be capable of providing visual or audible hints (e.g. pop-up text boxes; map markers for particular locations; highlighting around certain in-game objects; etc.) in response to a help request from the player (e.g. the player may press a particular key or button or select a particular menu item to indicate that help is required). A player may also seek help outside of the game, for example by submitting a help request through an app or web browser, in response to which advice or tutorials may be provided.

Examples described herein aim to provide an improved and/or more tailored response to help requests.

In one example of the present technique, there is provided an apparatus as set out in claim 1.

In another example of the present technique, there is provided a method as set out in claim 13.

In another example of the present technique, there is provided an entertainment device as set out in claim 14.

In another example of the present technique, there is provided a method as set out in claim 15.

Further respective aspects and features of the invention are defined in the appended claims.

Embodiments of the present invention will now be described by way of example with reference to the accompanying drawings, in which: Figure 1 illustrates an entertainment system; Figure 2 illustrates an apparatus for generating a help response; Figure 3 illustrates processing circuitry; Figure 4 illustrates lookup circuitry and a help-response library; Figure 5 illustrates use of a trained Al model to assist with looking up a help-response library; Figure 6 illustrates training of the Al model of Figure 5; Figure 7 illustrates use of a trained Al model to assist with generating a help response; Figure 8 illustrates training of the Al model of Figure 7; Figures 9 to 12 are flow diagrams illustrating methods of generating a help response; and Figure 13 is a flow diagram illustrating a method of generating a help request.

For clarity of illustration, elements illustrated in the figures have not necessarily been drawn to scale. Further, where considered appropriate, reference numerals have been repeated among the figures to indicate corresponding or analogous elements.

Methods and systems are disclosed for generating a help response. In the following description, a number of specific details are presented in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to a person skilled in the art that these specific details need not be employed to practice the present invention. Conversely, specific details known to the person skilled in the art are omitted for the purposes of clarity where appropriate.

Further, in the present application, the words "comprising at least one of..." are used to mean that any one of the following options or any combination of the following options is included. For example, "at least one of: A; B and C" is intended to mean A or B or C or any combination of A, B and C (e.g. A and B or A and C or B and C).

As explained above, a player may request help with achieving a particular goal relating to a particular game. For example, a player may request help while or in relation to playing the game on an entertainment system.

Referring to Figure 1, an example of an entertainment system 10 is a computer or console such as the Sony® PlayStation 5® (PS5).

The entertainment system 10 comprises a central processor 20. This may be a single or multi core processor, for example comprising eight cores as in the PS5. The entertainment system also comprises a graphical processing unit or GPU 30. The GPU can be physically separate to the CPU, or integrated with the CPU as a system on a chip (SoC) as in the PS5. The central processor 20 and/or the GPU 30 may be an example of processing circuitry to process a game state of a game.

The entertainment device also comprises RAM 40, and may either have separate RAM for each of the CPU and GPU, or shared RAM as in the PS5. The or each RAM can be physically separate, or integrated as part of an SoC as in the PS5. Further storage is provided by a disk 50, either as an external or internal hard drive, or as an external solid state drive, or an internal solid state drive as in the PS5.

The entertainment device may transmit or receive data via one or more data ports 60, such as a USB port, Ethernet® port, Wi-Fi® port, Bluetooth® port or similar, as appropriate. It may also optionally receive data via an optical drive 70.

Audio/visual outputs from the entertainment device are typically provided through one or more A/V ports 90, or through one or more of the wired or wireless data ports 60.

An example of a device for displaying images output by the entertainment system is a head mounted display 1-IM D' 120, such as the PlayStation VR 2 PSVR2', worn by a user 1.

Where components are not integrated, they may be connected as appropriate either by a dedicated data link or via a bus 100.

Interaction with the system is typically provided using one or more handheld controllers (130, 130A), such as the DualSense® controller (130) in the case of the PS5, and/or one or more VR controllers (130A-L,R) in the case of the HMD.

While playing a game using the entertainment system 10, a player may perform an action (e.g. pressing a particular button or combination of buttons on a handheld controller 130, 130A, e.g. to select a particular option on a menu) which triggers generation of a help request. The help request indicates a particular goal, in the game, that the player wishes to achieve; for example, the goal could be a particular level, location, or object that the player wishes to reach in the game, a particular enemy that the player wishes to defeat in the game, a particular map location that the player wishes to visit in the game, a particular task or quest that the user wishes to progress in, or any other goal or target the player wishes to achieve in the game. The help request could be generated by circuitry of the entertainment system (such as the central processor 20). For example, the player may press a button on the handheld controller 130, 130A and/or select an option on an in-game menu indicating that help is required, and the central processor 20 may respond to this selection by generating and sending a help request. Alternatively, the central processor 20 may generate the help request in response to detecting that a given condition has been satisfied -for example, the given condition could be an amount of time spent in-game without achieving a particular goal (implying that the player is stuck). Note that, the help request may also be triggered by a user input detected at a time other than when the player is playing the game -for example, the player may access a specific app or browser using the entertainment system 10. Hence, the central processor 20 may be an example of help request generating circuitry to generate a help request associated with the game, the help request indicating a goal to be achieved in the game, and to associate, with the help request, one or more help parameters (to be discussed below).

The help request may be entirely contextual -for example the choice to request help at a certain point in the game (or in a certain game state) may be sufficient to determine the type of help needed. Alternatively or in addition the help request may be partially contextual -for example based on the game state, the desired help may relate to how to defeat an enemy or how to escape from that enemy, or how to find a treasure item located near that enemy. In this case several help request options may be provided for selection by the user. Alternatively or in addition, the help request may be entirely user driven, for example by use of a text input allowing the user to specify a help request.

In other examples, the help request may not originate from an entertainment system for example, the player may access an app or web browser using a mobile device or other computer, and may provide inputs similar to one or more of those described herein which trigger the generation of a help request.

However the help request is generated, it is received by communication circuitry of an apparatus according to the present technique. An example of such an apparatus 200 is shown in Figure 2. The apparatus 200 comprises communication circuitry 210 to receive the help request -the communication circuitry 210 being, therefore, an example of communication circuitry to receive a help request associated with a game, the help request indicating a goal to be achieved in the game.

The apparatus 200 also comprises processing circuitry 220 -for example, this could be a central processor (CPU) similar to that shown in Figure 1 -to generate a help response based on the help request. The help response can take any of a number of forms -for example, if the help request is issued from within the game, the help response could include information indicative of an audible cue (which may be playable through a speaker or headphones connected to the entertainment system), a visual cue (which could be displayed on a display connected ot the entertainment system -this could be the HMD 120, for example) or haptic cue (which could be generated by one or the handheld controllers 130, 130, the HMD 120, or any other device held or worn by the player 1). Examples of help responses which can be provided to a user while they are playing the game include (but are not limited to) the following: * a pop-up text box displayed on-screen, providing advice or hints as to how to proceed; * other information in a pop-up, such as illustrations of buttons to press; * a map marker or route shown on a map in the game to direct the player to a particular in-game location; * on-screen direction cues (e.g. arrows) indicating a direction in which the player should travel/move; * highlighting around particular in-game objects; * haptic feedback to a controller or other object held or worn by a user; * any other information provided to the player to direct them to take particular actions in the game that are likely to help them to achieve their goal.

In other examples, the help-request may be issued from outside of the game, for example via an app or web browser. In such cases, help responses could include: * video, audio or text tutorials; * video, audio or text providing other information that may help the player to achieve the goal.

The system may provide these video, audio or text responses at the same time as providing the game, for example by re-sizing the game display area to create a space for the help response. Optionally the game may either pause or not pause whilst the help response is provided.

All of these help responses can be useful to a player looking to achieve a particular goal in a game, especially if they are not looking to achieve the goal in any specific way. However, sometimes, a player may wish to achieve a goal in a particular way -for example, they may wish to achieve the goal in the shortest time or using a specific tool or weapon. Similarly, the goal may be achieved (or better achieved) differently for different in-game player circumstances (e.g. depending on whether the player has chosen for their character to be a wizard or a soldier, or they have or do not have certain equipment or capabilities). In these circumstances the player is also in effect wishing to achieve the goal in a particular way (i.e. whilst being in their current in-game player circumstances) even if this is not a deliberate or conscious wish.

In either case, the apparatus 200 provides a mechanism to address this. In examples of the present technique, when a user (player) wants to do things a certain way -e.g. to achieve a given goal in the shortest time or with a specific weapon -a help request is parameterised with information about how the user wishes to achieve the goal (e.g. one or more help parameters are associated with the help request, and may also be received by the communication circuitry 210).

The one or more help parameters indicate additional conditions which the player intends (whether consciously or unconsciously) to meet while achieving the goal -for example, the processing circuitry 220 may be configured to identify, based on the one or more help parameters, one or more conditions to be satisfied by the player while achieving the goal in the game. The processing circuitry 220 is then arranged to generate the help response based on both the help request and the one or more parameters. The processing circuitry 220 is an example of processing circuitry to generate, based on the help request, a help response, wherein the processing circuitry is responsive to one or more help parameters associated with the help request to generate the help response in dependence on the one or more help parameters.

The apparatus 200 also includes lookup circuitry 230 to consult a help-response library 240 (which could, for example, store footage taken from other players who achieved the same goal) to identify the best match (which can then be provided to the player, or used by the processing circuitry 220 to generate a help response). The lookup circuitry is an example of lookup circuitry to look up, based on the help request and the one or more help parameters received by the communication circuitry, a help-response library to identify help information. The help-response library 240 is storage circuitry to store help information for use by the processing circuitry 220 to generate help responses, and is shown in Figure 2 as being outside of the apparatus 200 -in this example, the apparatus communicates with the help-response library 240 via a communication link 250, which could be a wired or a wireless link. However, in other examples the help-response library 240 could be part of (integrated with) the apparatus 200.

The help-response library 240 stores help information which can be used, by the processing circuitry, to generate the help response. For example, the help-response library could comprise exemplar help responses, which could be help responses generated, either by the processing circuitry 220 or by some other entity, in response to example help requests.

The exemplar help responses may be tagged based on their corresponding example help requests (e.g. by information indicating the goal specified by the corresponding request) and any help parameters associated with the corresponding example help requests (e.g. by information about the particular way the player wished to achieve the goal). To limit video storage overhead, one or more exemplar videos may be stored for each goal, and the exemplar videos can be evaluated and replaced with better examples as they occur -for example, each time the processing circuitry generates a help response, this could be compared with exemplar help responses stored in the help-response library to determine if it should also be stored to the help-response library (either in place of or in addition to any exemplar help responses already stored in the help-response library). To balance storage overhead and relevance of the help response, exemplar videos can be stored for a goal for different particular ways of achieving that goal; so if the goal can be achieved the same way by all players then optionally only one video is needed, whereas if different classes of in-game character can (or need to) achieve the goal in different ways then different videos may be stored, or similarly if the player wanted to achieve the goal whilst collecting all items, or in the shortest time. In each case better examples can replace earlier ones (for example based on time taken, score accrued, smallest damage taken, or a weighted combination of such performance metrics).

The lookup circuitry 230 looks up the help-response library to locate help information that can be used by the processing circuitry to generate a help response. For example, the lookup circuitry may look up the help-response library 240 based on the help request and parameter(s) received by the communication circuitry 210. The identified help information can then be retrieved and used, by the processing circuitry 220, to generate a help response to the help request received by the communication circuitry 210. For example, if an exemplar help response stored in the help-response library is identified which matches the goal specified by the help request and the associated parameter(s), the processing circuitry may simply provide this exemplar help response as the help response. In other examples, the processing circuitry 220 may be arranged to split and merge exemplar videos to compile the fullest footage of the activity (for example, if no exact match was found in the help-response library 240 but one or more partial matches were found).

The help response, once generated by the processing circuitry 230, may then be sent, by the communication circuitry 210, back to the device which issued the help request.

The apparatus 200 may be separate to the entertainment system 10 shown in Figure 1 -for example, the entertainment system 10 may be arranged to send, via the data port 60, a help request to the apparatus 200, which may for example be a server providing help responses. However, in other examples, the apparatus 200 is integrated with the entertainment system 10. For example, the communication circuitry 210 could be provided by the bus 100 of the entertainment system 10, and the processing circuitry 220 could be a processor such as the central processor 20 of the entertainment system 10.

Figure 3 schematically illustrates an example of the generation of a help response by the processing circuitry 220. As shown in this figure, the processing circuitry 220 receives a help request indicating a goal to be achieved in a game, and also receives one or more help parameters (referred to in Figure 3 as "parameter(s)") associated with the help request. The help request and the parameter(s) are received from the communication circuitry 210. Note that the help request could also indicate additional information -for example, it could identify the game to which it relates, the player on behalf of whom the request has been issued, information about the player's progress through the game, etc. The processing circuitry 220 also receives, from the help-response library 240 (optionally via the lookup circuitry or library access circuitry), help information identified by the lookup circuitry 230. For example, this help information could include one or more exemplar help responses.

Note that in some examples the processing circuitry 220 may not necessarily receive the help request and parameter(s) directly, but may instead receive some information derived from the help request and parameter(s) (such as an inference made by an artificial intelligence (Al) model).

Based on these inputs, the processing circuitry 220 generates a help response, and outputs this (e.g. to the communication circuitry 210).

Figure 4 schematically illustrates operation of example lookup circuitry 230. In this example, the lookup circuitry 230 receives the help request and the one or more associated help parameters (or information derived from the help request and the parameter(s), such as an inference made by an Al model). For example, this information could be received from the processing circuitry 220 or the communication circuitry 210. The lookup circuitry then looks up the help-response library 240 based on the help request and the parameters. In this particular example, the lookup circuitry comprises comparison circuitry 400 to compare the goal specified by the help request and the one or more associated help parameters with tags associated with information stored in the help-response library. Based on these comparisons, the lookup circuitry identifies help information in the help-response library. The lookup circuitry then either accesses the identified help information in the help-response library and provides this to the processing circuitry, or it outputs information identifying the help information to library access circuitry or to the processing circuitry.

In some examples, a trained artificial intelligence (Al) model may be used to assist with selecting the help information to be retrieved from the help-response library and used to generate the help response. An example of an Al model that can be used in this way is illustrated in Figures 5 and 6. The Al model 500 shown in these figures comprises a program executed on processing circuitry -this could be the same processing circuitry 220 described above, or it could be separate processing circuitry, such as a dedicated neural processing unit (N PU).

As shown in Figure 5, a trained Al model 500 may be provided with input data based on the goal identified by the help request and the associated parameter(s). For example, the input data may be generated or compiled by the processing circuitry 220. Based on this input data, the trained Al model 500 generates an inference which can be used, by the lookup circuitry 230, to identify the help information to be provided to the processing circuitry.

The trained Al model 500 can take any of a number of different forms. For example, it could be a machine learning (ML) model. In particular examples, the trained Al model 500 could be a computer vision model -for example, if the help information stored in the help-response library 240 comprises image data (e.g. video data such as tutorial videos or gameplay videos), a computer vision Al model could be used to analyse the help information (e.g. analysing player inventories, skill trees, etc.) to identify the help information to be provided to the processing circuitry. Note that a computer vision Al model is a type of Al program which can analyse and make an inference based on visual inputs (such as image data, which may include still and moving images (videos)).

Figure 6 illustrates an example of how the Al model 500 may be trained. For example, as shown in Figure 6, the Al model could be provided with training data including help requests and their associated help parameters, help responses, example gameplay context/recordings/screenshots, and information indicating links between different items of training data (e.g. information indicating whether the help responses are associated with particular help requests and/or particular help parameters).

It will be appreciated that such Al systems may be of particular use for legacy games that are not able to provide help parameters themselves because they were produced before, or without reference to, the techniques herein. In these cases the Al can be used to determine one or more relevant aspects of the game state useable to generate help parameters, such as visual indications of in-game location, character class, and/or equipment load-out (e.g. using visual feature matching), and / or status elements such as player health or active quests, for example using pattern matching, text recognition, or the like. The system may then operate generally as described elsewhere herein.

Another way in which a trained Al model can be used to support the present technique is in the generation of the help response by the processing circuitry 200. Figures 7 and 8 show an example of using a trained Al model in this way. As above, the Al model 700 comprises a program executed on processing circuitry, and this could be the same processing circuitry 220 described above, or it could be separate processing circuitry (such as a dedicated NPU).

As shown in Figure 7, a trained Al model 700 may generate an inference which can be used by the processing circuitry 220 to generate the help response. For example, the trained Al model 700 may receive input data based on help information obtained from the help-response library (referred to in the figure as a "help library"), the help request and the associated help parameter(s). As with the Al model shown in Figures 5 and 6, the Al model 700 could take any of a number of forms -for example, it could be an ML model.

Figure 8 illustrates an example of how the Al model 700 may be trained. For example, as shown in Figure 8, the Al model could be provided with training data including help requests and their associated parameters, help responses, example gameplay context / recordings / screenshots, information indicating links between different items of training data (e.g. information indicating whether the help responses are associated with particular help requests and/or particular help parameters). Note that the training data used for the Al model 700 in Figures 7 and 8 may be similar to that used for the Al model 500 in Figures 5 and 6. However, the training data may be formatted differently in each case, or annotated with different information. For example, the training data for the Al model shown in Figures 7 and 8 may be annotated with information indicating that the desired output is an inference from which a suitable help response can be generated, whereas the training data for the Al model shown in Figures 5 and 6 may be annotated with information indicating that the desired outcome is an inference from which useful help information can be identified.

While separate Al models are described above for assisting with identifying help information (Figures 5 and 6) and for assisting with generating a help response (Figures 7 and 8), it will be appreciated that in some embodiments a single Al model may be provided for performing both functions -for example, a single Al model (executed on processing circuitry) may perform the functions of the processing circuitry 220 and the lookup circuitry 230. Moreover, while examples have been described above which make use of trained Al models to identify help information in the help-response library and/or to generate a help response, it will be appreciated that this is just one example of how the present technique can be implemented. Other embodiments may not make use of Al at all.

Figures 9 to 13 are flow diagrams illustrating example methods of the present technique. In particular, Figures 9 to 12 illustrates methods of generating a help response in response to a help request, while Figure 13 illustrates a method of generating a help request.

In the method of Figure 9, a help request and one or more associated parameters are received 900, and a help response is generated 910 based on the help request and the help parameters.

Figure 10 shows a specific example of the method shown in Figure 9. In the method of Figure 10, the help request and associated parameter(s) are received 900, and the help-response library is searched 1000 to find help information to be used to generate the help response. In this particular example, the help information stored in the help-response library takes the form of exemplar help responses.

It is then determined 1010 whether a complete match can be found (e.g. whether the tags of any of the help information in the help-response library match both the help response and the one or more associated help parameters). For example, the lookup circuitry may provide, to the processing circuitry, a relevance indication indicative of a relevance of any identified help information to the help request and the one or more parameters received by the communication circuitry, the relevance indication being dependent on the comparison made by the comparison circuitry of the lookup circuitry. The relevance indication may be used by the processing circuitry to perform the determinations in steps 1010 and 1030 of Figure 10.

If ("Y" branch) a complete match can be found (e.g. if the relevance indication indicates that a complete match has been found), the matching exemplar help response is provided 1020 as the help response to the received help request.

On the other hand, if a complete match cannot be found ("N" branch), it is determined 1030 whether any partial matches (e.g. any help responses with tags matching the help request but not all of the associated help parameters, or with tags matching one or more of the associated parameters but not the help request) can be found. If it is determined that one or more partial matches can be found ("Y" branch) (e.g. if the relevance indication indicates that a partial match has been found), the identified exemplar help responses are used to generate 1040 the help response to the received help request. For example, the help response may be generated by splitting and merging multiple help-responses.

If no complete matches (step 1010 "N" branch) and no partial matches (step 1030 "N" branch) can be found, the method includes a step 1050 of either returning an error response, or generating the help response using some other process.

Figure 11 illustrates a method which makes use of the Al model 700 shown in Figures 7 and 8. In this method, a help request and one or more associated help parameters are received 900, and the help-response library is searched 1000 based on this information. Input data for the trained Al model is generated 1100 based on the received help request, the one or more associated parameters and an indication of any complete (full) or partial matches detected in the help-response library. The input data is provided 1110 to the trained Al model, and the method waits 1120 to receive an inference generated by the Al model. Once the inference has been received ("Y" branch), a help response is generated 1130 based on the inference.

Figure 12 illustrates a method which makes use of the Al model 500 shown in Figures 5 and 6. In this method, a help request and one or more associated parameters are received 900, and these are used to generate 1200 input data for the trained Al model. The input data is provided 1210 to the Al model, and the method waits 1220 to receive an inference from the Al model. Once this inference has been received ("Y" branch), it is used to identify 1230 help information in the help-response library. The identified help information is obtained 1240 from the help-response library and a help response is generated 1250 based on the obtained help information.

Each of the methods shown in Figures 9 to 12 is an example of a method comprising: * receiving a help request associated with a game, the help request indicating a goal to be achieved in the game; and * generating, based on the help request and one or more help parameters associated with the help request, a help response. Figure 13 illustrates a method of generating a help request. As shown in Figure 13, a help request is generated 1300 and one or more help parameters are associated 1310 with the request. The generated help request and the one or more associated help parameters are then output 1320. This is an example of a method comprising: * generating a help request associated with a game, the help request indicating a goal to be achieved in the game; * associating, with the help request, one or more help parameters; and * outputting the help request and the one or more help parameters associated with the help request.

Any of the above methods (e.g. those shown in Figures 9 to 13) can be performed, for example, by a computer executing instructions of a computer program. For example, a computer program may be provided which comprises instructions which, when executed by a computer, causes the computer to perform any one of the above methods. The computer program could be stored on a transitory or a non-transitory medium.

The apparatuses and methods described above provide mechanisms by which a help response can be generated, in response to a help request, based on not only the goal specified by the help request but also any parameters associated with the help request. This makes it possible to generate help responses which can help a player to achieve a desired goal in a game in a particular way (such as in a particular time, with a particular tool or weapon, at a particular difficulty level, etc.).

Claims

CLAIMS1. An apparatus comprising: communication circuitry to receive a help request associated with a game, the help request indicating a goal to be achieved in the game; and processing circuitry to generate, based on the help request, a help response, wherein the processing circuitry is responsive to one or more help parameters associated with the help request to generate the help response in dependence on the one or more help parameters.
2. The apparatus of claim 1, wherein the processing circuitry is configured to identify, based on the one or more help parameters, one or more conditions to be satisfied by the player while achieving the goal in the game.
3. The apparatus of claim 1 or claim 2, comprising lookup circuitry to look up, based on the help request and the one or more help parameters received by the communication circuitry, a help-response library to identify help information, wherein the processing circuitry is configured to generate the help response using the help information obtained from the help-response library.
4. The apparatus of claim 3, wherein the lookup circuitry is configured to look up the help-response library to obtain, as the help information, information indicative of one or more exemplar help responses.
5. The apparatus of claim 3 or claim 4, wherein: the lookup circuitry comprises comparison circuitry to perform a comparison to compare (a) the help request and the one or more help parameters received by the communication circuitry with (b) information stored in the help response library; and the lookup circuitry is configured to identify, in dependence on the comparison, the help information to be obtained from the help-response library.
6. The apparatus of any of claims 3 to 5, wherein: the processing circuitry is configured to provide, to a trained artificial intelligence program, input data comprising the help request and the one or more help parameters; and the lookup circuitry is configured to identify, based on an inference made by the trained artificial intelligence program in dependence on the input data, the help information to be obtained from the help response library.
7. The apparatus of claim 6, wherein the trained artificial intelligence program is configured to review the help information stored in the help response library to identify one or more most relevant exemplar help responses.
8. The apparatus of claim 7, wherein: the help information comprises image data; and the trained artificial intelligence program comprises a trained computer-vision artificial intelligence program configured to process the image data to identify the one or more most relevant exemplar help responses.
9. The apparatus of any of claims 5 to 8, wherein: the lookup circuitry is configured to provide, to the processing circuitry, a relevance indication indicative of a relevance of the identified help information to the help request and the one or more help parameters received by the communication circuitry, the relevance indication being dependent on the comparison; and the processing circuitry is configured to generate the help response in dependence on the help information obtained from the help-response library and the relevance indication.
10. The apparatus of claim 9, wherein the processing circuitry is responsive to the relevance indication indicating a complete match between (a) the identified help information and (b) the help request and the one or more parameters received by the communication circuitry to output, as the help response, a exemplar help response corresponding to the identified help information.
11. The apparatus of claim 9 or claim 10, wherein the processing circuitry is responsive to the relevance indication indicating a partial match between (a) the identified help information and (b) the help request and the one or more parameters received by the communication circuitry to generate the response by combining information associated with two or more exemplar help response.
12. The apparatus of any of claims 9 to 11, wherein the processing circuitry is responsive to the relevance indication indicating an absence of a complete match between (a) the identified help information and (b) the help request and the one or more parameters received by the communication circuitry to: provide, as inputs to a trained artificial intelligence program, the identified help information, the help request and the one or more parameters; and generate the help response in dependence on an inference made by the trained machine learning algorithm.
13. A method comprising: receiving a help request associated with a game, the help request indicating a goal to be achieved in the game; and generating, based on the help request and one or more help parameters associated with the help request, a help response.
14. An entertainment system comprising: processing circuitry to process a game state of a game; help request generating circuitry to: generate a help request associated with the game, the help request indicating a goal to be achieved in the game; and associate, with the help request, one or more help parameters; and communication circuitry to output the help request and the one or more help parameters associated with the help request.
15. A method comprising: processing a game state or a game; generating a help request associated with the game, the help request indicating a goal to be achieved in the game; associating, with the help request, one or more help parameters; and outputting the help request and the one or more help parameters associated with the help request.