Air Treatment Control

Abstract

A controller and a method of operating a controller for a shared space air treatment apparatus configured to control air treatment in one or more zones comprises a recognition system operable to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus; a comparator operable to compare a stored air characteristic value associated with the person and a sensed air characteristic value associated with the zone; and a transceiver operable to send at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

Description

FIELD

[0001] The present technology relates to air treatment apparatus, and particularly to methods of, and apparatus for, providing personalized treated air to individuals in a shared space.BACKGROUND

[0002] Shared spaces, such as offices and meeting rooms typically have a provided air supply that is set to a single temperature, humidity level, etc. for the whole space, and this is often not in accordance with the preferences of all the individuals using the shared space. Some prefer (and are more comfortable and / or work more efficiently when provided with) a higher or lower temperature, a higher or lower humidity level, a higher or lower air movement value, and the like.SUMMARY

[0003] There is thus provided according to a first approach, a controller for a shared space air treatment apparatus configured to control air treatment in one or more zones, comprising: a recognition system operable to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus; a comparator operable to compare a stored air characteristic value associated with the said person and a sensed air characteristic value associated with the zone; and a transceiver operable to send at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

[0004] In a second approach, there is provided a method of operating a controller for a shared space air treatment apparatus, comprising: using a recognition system to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus; comparing, by a comparator, a stored air characteristic value associated with the said person and a sensed air characteristic associated with the zone; and sending, by a transceiver, at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

[0005] A further approach provides a computer program product stored on a non-transitory computer readable medium and comprising computer program code to use a recognition system to identify the presence of a person at a location associated with an air supply treatment zone of a shared space air treatment apparatus; compare a stored air characteristic value associated with the said person and a sensed air characteristic associated with the zone; and send, by a transceiver, at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

[0006] There is thus provided an apparatus for providing treated air in shared spaces that is capable of recognizing an individual person at a particular position in relation to the apparatus, associating air treatment preferences with the individual person, and operating an air treatment apparatus and an air supply outlet for that position in accordance with the air treatment preferences of the individual person.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Various embodiments of the technology described herein will now be described, by way of example only and not by way of limitation, with reference to the accompanying drawings, in which:

[0008] FIG. 1 shows a much-simplified high-level view of an example controller for a shared space air treatment apparatus according to an implementation of the present technology;

[0009] FIG. 2 shows a much-simplified view of an example of a plurality of shared space air treatment apparatus in electronic communication according to an implementation of the present technology; and

[0010] FIG. 3 shows the main elements of a method of operating a controller for a shared space air treatment apparatus according to an implementation of the present technology.DETAILED DESCRIPTION

[0011] Reference is made in the following detailed description to accompanying drawings, which form a part hereof, wherein like numerals may designate like parts throughout that are corresponding and / or analogous. It will be appreciated that the figures have not necessarily been drawn to scale, such as for simplicity and / or clarity of illustration. For example, dimensions of some aspects may be exaggerated relative to others. Other embodiments may be utilized, and structural and / or other changes may be made without departing from claimed subject matter. References throughout this specification to “claimed subject matter” refer to subject matter intended to be covered by one or more claims, or any portion thereof, and are not necessarily intended to refer to a complete claim set, to a particular combination of claim sets (e.g., method claims, apparatus claims, etc.), or to a particular claim. Directions and / or references, for example, such as up, down, top, bottom, and so on, may be used to facilitate discussion of drawings and are not intended to restrict application of claimed subject matter. The following detailed description therefore does not limit the claimed subject matter and / or equivalents.

[0012] In the following detailed description of example embodiments, reference is made to specific example embodiments by way of drawings and illustrations. These examples are described in sufficient detail to enable those skilled in the art to practice what is described, and serve to illustrate how elements of these examples may be applied to various purposes or embodiments. Other embodiments exist, and logical, mechanical, electrical, and other changes may be made. Features or limitations of various embodiments described herein, however important to the example embodiments in which they are incorporated, do not limit other embodiments, and any reference to the elements, operation, and application of the examples serves only to aid in understanding these example embodiments. Features or elements shown in various examples described herein can be combined in ways other than shown in the examples, and any such combinations is explicitly contemplated to be within the scope of the examples presented here.

[0013] Those who work in shared spaces often find that the characteristics of the air in their surroundings is not what they would prefer. The levels of discomfort may vary—for example, some office workers find that the “normal” temperature of the open office is so low that they are obliged to wear extra clothes, or so humid that they find it unbearable, and this gives them a very uncomfortable experience in the office environment. For others, the air may feel dry, and this may vary from no more than a mild irritant to a major problem, causing dry eyes and skin.

[0014] In any case, because the space is shared, there is a common perception that all those who share the space must simply “put up with” whatever air characteristics are set for the whole space. Typically, for example, the temperature of offices may be set according to a notional preferred temperature determined statistically some years ago as being acceptable for the 90th percentile portion of the male population. This “one size fits all” approach can lead to significant difficulties for some of the users of shared spaces.

[0015] In accordance with the present technology, by contrast, it is possible to zone the shared space, and thereby to provide individual persons with the air characteristics, such as temperature, humidity and flow rate, that are as near as possible to the characteristics that make them most comfortable.

[0016] It is further preferable to provide a means for controlling these matters that does not require manual setting of controls for each of the characteristics each time a person enters a zone or moves from one zone to another.

[0017] Implementations of the present technology address the matters stated above by applying a machine learning and inferencing technology to provide air quality tailored for individuals in the shared air space.

[0018] In FIG. 1 there is shown a block diagram of an example controller 102 for a shared space 100 air treatment apparatus 104. The controller 102 is arranged in the shared space 100 and configured to be in electronic communication by way of transceiver 118 and comms (communications) channel 120 with the air treatment apparatus 104.

[0019] Transceiver 118 and comms channel 120 may comprise communication circuitry suitable for wireless communication, such as, for example, one or more of: wireless local area network (Wi-Fi®); short range communication such as radio frequency communication (RFID); near field communication (NFC); communications used in wireless technologies such as Bluetooth®, Bluetooth Low Energy (BLE); or cellular communications such as 3G or 4G. The communication circuitry may alternatively or additionally use wired communication such as a fibre optic or metal cable. The communication circuitry could use two or more different forms of communication, such as two or more of the examples given above in combination.

[0020] The controller 102 comprises a recogniser 106 configured to identify the presence of a specific person 108 at a location associated with an air treatment zone-ambient air zone 110, in the example-of the shared space 100 air treatment apparatus 104. The recogniser 106 may comprise, for example, a facial or overall shape recognition system, a gait recognition system, a system for detecting a portable, wearable, or implanted identifying device, such as a personal electronic ID tag or a mobile telephone, or the like.

[0021] In one example implementation, the recogniser 106 may be operable in the form of a combination of an image capture device (such as a camera) and an analysis engine, which may be implemented using an artificial intelligence (AI) machine learning (ML) and inferencing system. The recogniser 106 of this implementation captures an image of a region of the shared space 100 and establishes that it relates to an ambient air zone 110; the recogniser 106 then isolates the face by inferencing from the image background. The isolated face image is then normalised to allow for its position, angle of rotation, light / shade, and the like. The normalised face image is then analysed by inferencing to extract the identifying characteristics of features such as the eyes, nose and mouth to create a feature vector that can be compared with the feature data for specific persons stored in the data store 114. In a similar fashion, a gait recogniser may capture and analyse a sequence of images of the person moving into the zone of interest to extract gait data that can be used to identify the specific person.

[0022] In another example, the recogniser 106 may act in conjunction with a wireless receiver operable to receive a transmitted identifier of a specific person—for example, the person may have an identification tag (for example, a radio frequency identification tag) or other device that is operable to respond to interrogation over a communications means, such as a wireless channel, with an identifier. Such a tag may, for example, be wearable, portable or implanted.

[0023] The controller 102 thus further comprises a data store 114 operable to store and permit retrieval of data relating to specific persons 108, including recognition data suitable for use by the recogniser 106 and associated data relating to characteristics and preferences of the specific person 108. Examples of the characteristics and preferences of specific persons 108 include preferred air temperatures, preferred humidity levels, preferred air movement speed, and the like. The data store 114 may be modifiable according to new data for the said person learned by the recogniser 106 during operation of the controller 102 for the shared space 100 air treatment apparatus 104. The data store 114 may also be stored locally to the controller 102 or in a remote location accessible to the controller 102, for example over a wired or wireless communications network.

[0024] The controller 102 further comprises a sensor 116 operable to sense the air characteristics of ambient air zone 110 of the shared space 100—for example, sensor 116 may comprise an infrared temperature sensor or the like, operable to detect the relevant characteristics of the air in ambient air zone 110 of the shared space 100. In another example, the sensor 116 may comprise a humidity sensor operable to detect the humidity of the air in the ambient air zone 110.

[0025] The recogniser 106 and the sensor 116 are operable to communicate their findings to a comparator 112 which is configured to retrieve from data store 114 a stored air characteristic value associated with the identified specific person 108 recognised to be at the location in ambient air zone 110, and a sensed air characteristic value (as sensed by sensor 116 associated with the ambient air zone 110.

[0026] The comparator 112 compares the stored air characteristic value for the specific person 108 with the air characteristics of ambient air zone 110 of the shared space 100 as received from sensor 116 to detect equality or inequality—that is, the comparator examines the person's stored air characteristic value, such as a preference for a temperature or humidity level, or the like, with the actual sensed air characteristic value, to determine whether the air treatment provided by air treatment apparatus 104 requires adjustment to meet the needs of the specific person 108.

[0027] In this way, the controller 102 identifies the presence of, and recognises, a specific person 108 in relation to a specific zone 110 of the shared space, and retrieves a stored air characteristic (such as a preferred temperature, for example) for that specific person. The controller 102 then operates a sensor 116 to sense an actual air characteristic for the ambient air zone 110 where the specific person 108 has been detected, and compares the stored characteristic with the actual characteristic, to decide whether an adjustment is necessary to bring them into substantial equality.

[0028] When the controller 102 determines that the outcome of the comparison by comparator 112 is that an adjustment is needed, the controller 102 constructs an appropriate instruction to be sent over comms channel 120 to air treatment apparatus 104. The controller further comprises a transceiver 118 operable to send at least one such adjustment instruction for the air treatment apparatus 104 over the comms channel 120 to cause the air treatment apparatus 104 to adjust a target air characteristic value for the associated ambient air zone 110 and thus control air treatment apparatus 104 based on the comparison of the stored air characteristic value and the sensed air characteristic value.

[0029] In a variant, the inferencing of the present technology may still provide an outcome even when an individual is not perfectly recognisable in this way—for example, sufficient indicators may be extracted to determine that a person may be over a particular age, and as it is known that older individuals may require a warmer environment than others, a generalised conclusion may be drawn, and an instruction may be given to bring a temperature of the ambient air zone to a higher than a preset default value.

[0030] Thus, the controller 102 may be operable, in the absence of stored recognition and / or stored air characteristic data for the specific person 108, to interrogate the data store 114 for any gathered characteristic data for the recognised person or determined class of person, and to send an adjustment instruction to adjust the air treatment apparatus 104 according to the gathered characteristic data for the person or class of persons. Gathered characteristic data may include historical data relating to manual adjustments made over a period by members of an identifiable group of persons—for example, where a group of persons have a history of turning up the thermostat control of a room each time one of the group enters that room, that data may be stored and used at a later time by controller 102.

[0031] For example, the adjustment instruction may tell an air treatment apparatus 104 to cool or heat the emitted air, to humidify or dehumidify the emitted air, to emit the air at an increased or decreased flow rate, and the like.

[0032] Further, because the controller 102 of the present technology is provided with a degree of artificial intelligence, it is further capable of detecting that a specific person 108 identified within an ambient air zone has moved away. It may then be operable to, for example, allow the treated air characteristics for the zone to revert to a default setting.

[0033] It may further be operable to communicate with further controller instances that may be located in other shared spaces, such that, for example, another controller, on detection of a person moving into a particular ambient air zone of its shared space, may pass the recognition data and request a response containing any stored air characteristic value associated with the person via the transceiver 118 and comms channel 120 to its peer controllers who may have stored data for that person. In this way. A controller may be set up in electronic communication with one or more further instances of controllers, and may pass the stored air characteristic value for that person to the one or more further instances when the person moves from one location to another.

[0034] As will be immediately clear to one of ordinary skill in the art, the arrangement depicted in FIG. 1 has been much simplified for convenience as an example. In a real world setting, the structures of the arrangement may be separated into plural distributed units or combined into subassemblies of units, and there may be additional complexities and intermediate elements in their interconnects that are not shown in the figure.

[0035] FIG. 2 shows an example of a plurality of shared space air treatment apparatus in electronic communication according to an implementation of the present technology. In the example implementation of FIG. 2, there is shown a pair of shared spaces 100 and 100′. Shared space 100, as in FIG. 1, comprises a controller 102 and an air treatment apparatus 104, in electronic communication via transceiver 118 with comms channel 120. Shared space 100′ comprises a controller 102′ and an air treatment apparatus 104′, in electronic communication with comms channel 120′, which in turn is arranged in electronic communication with comms channel 120 of shared space 100.

[0036] If person 108 is detected as leaving shared space 100 and is detected entering ambient air zone 110′ of shared space 100′, comms channels 120 and 120′ may be used to pass requests and responses between shared spaces 100 and 100′, so that controller 102 may pass recognition and stored air characteristic data for person 108 to controller 102′. Controller 102′ is then operable to send any necessary adjustment instructions for the air treatment apparatus 104 to adjust a target air characteristic value for the associated ambient air zone 110′ and thus control air treatment apparatus 104′ based on the comparison of the stored air characteristic value and the sensed air characteristic value, or according to the gathered characteristic data for the person or class of persons.

[0037] As will be immediately clear to one of ordinary skill in the art, the arrangement depicted in FIG. 2 has been much simplified for convenience as an example. In a real world setting, the structures of the arrangement may be separated into plural distributed units or combined into subassemblies of units, and there may be additional complexities and intermediate elements in their interconnects that are not shown in the figure.

[0038] Turning now to FIG. 3, there are shown the main elements of a method 200 of operating a controller 102 for a shared space 100 air treatment apparatus 104 according to an implementation of the present technology. As will be immediately clear to one of ordinary skill in the art, the depicted example has been much simplified for convenience, and, in particular, the person of ordinary skill in the art will recognise that in modern electronic computing systems processes shown as occurring in sequence in the figure may in reality be performed out of sequence or in parallel, using, for example, single instruction multiple data arrangements and the like.

[0039] The method 200 of operating controller 102 in FIG. 3 begins at START 202, which will be immediately understood by one of ordinary skill in the art to represent the beginning of a single instance of the method, which may iterate as necessary.

[0040] At 204, one or more zones in the shared space are monitored by controller 102 to detect (a) a person in movement or (b) a person in an ambient air zone.

[0041] If the monitoring at 204 detects a person moving, controller 102 further operates to recognise (where possible) the specific person (108 of FIGS. 1 and 2). If a person moving detected at test 206 is recognised, for example by facial or gait recognition, by identification tag, or the like, the controller 102 may search the data store 114 for data associated with specific person 108, and may at 208 pass that data on via a transceiver 118 connected to a communications channel to a further instance of the controller (102′ of FIG. 2). From 208, the process returns to monitoring the zone 204.

[0042] If at test step 206, the person is not detected in motion, but is detected in the zone 210, controller 102 further operates to recognise (where possible) the specific person (108 of FIGS. 1 and 2). If a person in the zone detected at 210 is recognised, for example by facial or gait recognition, by identification tag, or the like, the controller 102 may search the data store 114 to retrieve data associated with specific person 108, including any stored air characteristic value, such as a preferred air temperature, humidity level or flow rate, for example.

[0043] At 212, the controller 102 uses a sensor to sense one or more air characteristics in ambient air zone 110—for example, the sensor may detect an air temperature, a humidity level, an air flow rate, or the like. The derived air characteristic value Z may be held by the controller, for example in a working memory, scratchpad, cache, register or the like form of local storage for processing.

[0044] At 214, the controller 102 retrieves an air characteristic value P from the data store 114 as described above with reference to FIGS. 1 and 2. The retrieved air characteristic value P may be held by the controller, for example in a working memory, scratchpad, cache, register or the like form of local storage for processing.

[0045] At 218, the air characteristic values P and Z are compared to test for substantial equality (the substantiality test threshold being preset in a manner that will be immediately familiar to those of ordinary skill in the art).

[0046] If, at 218, the air characteristic values P and Z are found to be substantially equal, the process returns to monitor zone step 204. As will be clear to those of skill in the art, this iterative loop may then continue until terminated.

[0047] If at 218, the air characteristic values P and Z are found to be not substantially equal according to the preset substantiality test, the transceiver 118 at controller 102 is used at 220 to send an adjustment instruction or instructions via and comms channel 120 to air treatment apparatus 104 to adjust a target air characteristic value for the associated ambient air zone 110 and thus control air treatment apparatus 104 based on the comparison of the stored air characteristic value and the sensed air characteristic value.

[0048] In a concrete example, a person arrives at a desk in a shared seating area of an office, is detected and recognised as preferring an air temperature of 21 degrees Celsius. The sensor finds that the ambient temperature of the zone in which the person is sitting is 19 degrees Celsius, and the controller thus constructs and transmits an instruction to the relevant air treatment and supply apparatus to bring the air temperature in the zone to substantial equality with the preferred temperature of 21 degrees Celsius.

[0049] In a variant, the inferencing of the present technology may still provide an outcome even when an individual is not perfectly recognisable at 210—for example, sufficient indicators may be extracted to determine that a person is a member of a particular class, for example, the person's general appearance may indicate that the person is over a particular age, and as it is known that older individuals may require a warmer environment than others, a generalised conclusion may be drawn, and an instruction may be sent at 220 to instruct the air treatment apparatus to bring a temperature of the ambient air zone to a higher than a preset default value.

[0050] Thus, the controller 102 may be operable, in the absence of stored recognition and / or stored air characteristic data for the specific person 108, to also interrogate the data store 114 at 210 for any gathered characteristic data for the recognised person or determined class of person, and to cause the transceiver 118 to send an adjustment instruction 220 according to the gathered characteristic data for the person or class of persons. Gathered characteristic data may include historical data relating to manual adjustments made over a period by members of an identifiable group of persons—for example, where a group of persons have a history of turning up the thermostat control of a room each time one of the group enters that room, that data may be stored and used in a further iteration of method 200 at a later time.

[0051] After the adjustment instruction has been transmitted at 220 by transceiver 118, the present iteration of the method 200 ends at END 222. As will be clear to one of ordinary skill in the art, this means only that the present instance ends, and in a real world scenario, it is likely that the method 200 will be repeated from START 202 until some form of interruption, such as a system shutdown, takes place.

[0052] In a specific implementation, there may be provided a controller for a shared space air treatment apparatus, including a recognition system capable of identifying a person at a position relative to an air supply outlet; a store of data responsive to the identifying of the said person and comprising a stored air characteristic preference value for the person, a transceiver in electronic communication with a sensor to receive an actual air characteristic value local to the said person, a comparator that can compare the stored air characteristic preference value for the person and the air characteristic local to the said person, where the transceiver can then send an adjustment instruction to adjust the air supply outlet to bring the air characteristic value local to the said person to substantial equality with the stored air characteristic preference value for the person.

[0053] The apparatus is thus capable of recognizing an individual person at a particular position in relation to the apparatus, associating air treatment preferences with the individual person, and operating an air supply outlet for that position in accordance with the air treatment preferences of the individual person.

[0054] The present techniques comprise a recognition system which may comprise an AI ML and inferencing system, where the recognition system may use one or more ML models to provide the described functionality.

[0055] As will be clear to one of skill in the art, the term “ML models” used herein is intended to refer to the models used in intelligent model-based learning and inferencing systems. These models may be managed and operated using any of the known forms of intelligent machine learning elements to achieve the technical function of the present technology.

[0056] Such ML models are often used to process complex information such as videos streams, images and text in training and inferencing operations.

[0057] ML models may enable improved results in a wide range of tasks, including text, image, video and speech processing, just to provide a couple of example applications. To enable performing such tasks, features of a ML model may be structured and / or configured to form “filters” that may have a measurable / numerical state such as a value of an output signal. Such a filter may comprise nodes and / or edges arranged in “paths” and are to be responsive to sensor observations provided as input signals. In an implementation, a state and / or output signal of such a filter may indicate and / or infer detection of a presence or absence of a feature in an input signal.

[0058] In particular implementations, the ML model may comprise one or more neural networks (e.g., nodes, edges, weights, layers of nodes and edges), where intelligent computing devices to perform functions supported by neural networks may comprise a wide variety of stationary and / or mobile devices, such as, for example, smart mobile phones, wearable devices, Internet of things (IoT) devices, personal digital assistants (PDAs), virtual assistants, laptop computers, personal entertainment systems, tablet personal computers (PCs), PCs, just to provide a few examples.

[0059] According to an embodiment, a neural network may be structured in layers such that a node in a particular neural network layer may receive output signals from one or more nodes in an upstream layer in the neural network, and provide an output signal to one or more nodes in a downstream layer in the neural network. One specific class of layered neural networks may comprise a convolutional neural network (CNN) or space invariant artificial neural networks (SIANN) that enable deep learning. Such CNNs and / or SIANNs may be based, at least in part, on a shared-weight architecture of a convolution kernels that shift over input features and provide translation equivariant responses. Such CNNs and / or SIANNs may be applied to text, image and / or video recognition, recommender systems, image classification, image segmentation, medical image analysis, natural language processing, brain-computer interfaces, just to provide a few examples.

[0060] Another class of layered neural network may comprise a recursive neural network (RNN) that is a class of neural networks in which connections between nodes form a directed cyclic graph along a temporal sequence. Such a temporal sequence may enable modeling of temporal dynamic behavior. In an implementation, an RNN may employ an internal state (e.g., storage (memory)) to process variable length sequences of inputs. This may be applied, for example, to tasks such as unsegmented, connected handwriting recognition or speech recognition, just to provide a few examples. In particular implementations, an RNN may emulate temporal behavior using finite impulse response (FIR) or infinite impulse response (IIR) structures. An RNN may include additional structures to control stored states of such FIR and IIR structures to be aged. Structures to control such stored states may include a network or graph that incorporates time delays and / or has feedback loops, such as in long short-term memory networks (LSTMs) and gated recurrent units.

[0061] A neural network (NN) (e.g., CNN, RNN etc.) may have multiple hidden layers in order to model complex, nonlinear relationships between input data and output data, where such neural networks are referred to as deep neural networks (DNN).

[0062] Generally, classification networks, such as ANNs, CNNs, RNNs, etc., that perform pattern recognition (e.g., image, speech, activity, etc.) may be implemented in hardware, a combination of hardware and software, or software. Prediction is a fundamental element of many classification networks that include machine learning (ML), such as, for example, artificial neural networks (ANNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), Binary Neural Networks (BNN), Support Vector Machines (SVMs), Decision Trees, Bayesian networks, Naïve Bayes, etc.

[0063] The present technology may take the form of a computer program product embodied in a computer readable medium having computer readable program code embodied thereon. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be a non-transitory computer readable storage medium encoded with instructions that, when performed by a processing means, cause performance of the method described above. A computer readable medium may be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0064] Computer program code for carrying out operations of the present techniques may be written in any combination of one or more programming languages, including object-oriented programming languages and conventional procedural programming languages.

[0065] For example, program code for carrying out operations of the present techniques may comprise source, object, or executable code in a conventional programming language (interpreted or compiled) such as C, or assembly code, code for setting up or controlling an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array), or code for a hardware description language such as Verilog™, SystemVerilog, or VHDL (Very high speed integrated circuit Hardware Description Language).

[0066] The program code may execute entirely on the user's computer, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network. Code components may be embodied as procedures, methods, or the like, and may comprise sub-components which may take the form of instructions or sequences of instructions at any of the levels of abstraction, from the direct machine instructions of a native instruction set to high-level compiled or interpreted language constructs.

[0067] It will also be clear to one of skill in the art that all or part of a logical method according to the preferred embodiments of the present techniques may suitably be embodied in a logic apparatus comprising logic elements to perform the steps of the method, and that such logic elements may comprise components such as logic gates in, for example a programmable logic array or application-specific integrated circuit. Such a logic arrangement may further be embodied in enabling elements for temporarily or permanently establishing logic structures in such an array or circuit using, for example, a virtual hardware descriptor language, which may be stored and transmitted using fixed or transmittable carrier media.

[0068] In one alternative, an embodiment of the present techniques may be realized in the form of a computer implemented method of deploying a service comprising steps of deploying computer program code operable to, when deployed into a computer infrastructure or network and executed thereon, cause the computer system or network to perform all the steps of the method.

[0069] In a further alternative, the preferred embodiment of the present techniques may be realized in the form of a data carrier having functional data thereon, the functional data comprising functional computer data structures to, when loaded into a computer system or network and operated upon thereby, enable the computer system to perform all the steps of the method.

[0070] One or more of the controllers described above may implement the present technology in a computing-capable device such as a personal user device (e.g., a smartphone), although the claims are not limited in this respect.

[0071] In an illustrative example, the computing device may include an application that utilizes analysis architecture for processing data (e.g., text data, image data, speech data) generated or received at the computing device. Furthermore, the computing device may utilize plural analysis architectures for analysing two or more different types of data (i.e., multimodal data analysis).

[0072] The one or more analysis architecture(s) may, in some examples, be implemented in software and / or data structures, where various nodes, tensors, activation functions, and other elements of processing stages of a neural network may be stored in data structures in storage.

[0073] In other examples, the analysis architecture may be implemented in hardware, such as a convolutional neural network structure that is embodied within the transistors, resistors, and other elements of an integrated circuit. In an alternate example, the analysis architecture may be implemented in a combination of hardware and software, such as a neural processing unit (NPU) having software-configurable weights, network size and / or structure, and other such configuration parameters.

[0074] The analysis architecture as described herein in particular examples, may be formed in whole or in part by and / or expressed in transistors and / or lower metal interconnects (not shown) in processes (e.g., front end-of-line and / or back-end-of-line processes) such as processes to form complementary metal oxide semiconductor (CMOS) circuitry. The various blocks, neural networks, and other elements disclosed herein may be described using computer aided design tools and expressed (or represented), as data and / or instructions embodied in various computer-readable media, in terms of their behavioral, register transfer, logic component, transistor, layout geometries, and / or other characteristics. Formats of files and other objects in which such circuit expressions may be implemented include, but are not limited to, formats supporting behavioral languages such as C, Verilog, SystemVerilog, and VHDL, formats supporting register level description languages like RTL, and formats supporting geometry description languages such as GDSII, GDSIII, GDSIV, CIF, MEBES and any other suitable formats and languages. Storage media in which such formatted data and / or instructions may be embodied include, but are not limited to, non-volatile storage media in various forms (e.g., optical, magnetic or semiconductor storage media) and carrier waves that may be used to transfer such formatted data and / or instructions through wireless, optical, or wired signalling media or any combination thereof. Examples of transfers of such formatted data and / or instructions by carrier waves include, but are not limited to, transfers (uploads, downloads, e-mail, etc.) over the Internet and / or other computer networks via one or more data transfer protocols (e.g., HTTP, FTP, SMTP, etc.).

[0075] It will be clear to one skilled in the art that many improvements and modifications can be made to the foregoing exemplary embodiments without departing from the scope of the present techniques.

[0076] Features described in the preceding description may be used in combinations other than the combinations explicitly described.

[0077] Although functions have been described with reference to certain features, those functions may be performable by other features whether described or not.

[0078] Although features have been described with reference to certain embodiments, those features may also be present in other embodiments whether described or not.

Claims

1. A controller for a shared space air treatment apparatus configured to control air treatment in one or more zones, comprising:a recognition system operable to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus;a comparator operable to compare a stored air characteristic value associated with the said person and a sensed air characteristic value associated with the zone; anda transceiver operable to send at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

2. The controller according to claim 1, wherein the transceiver is operable to send at least one adjustment instruction to instruct at least one air supply outlet to supply cooled air.

3. The controller according to claim 1, wherein the recognition system comprises a facial recognition machine learning and inferencing system.

4. The controller according to claim 1, wherein the recognition system comprises a wireless receiver operable to receive a transmitted identifier of the said person.

5. The controller according to claim 1, wherein the store of data is modifiable according to new data for the said person learned by the recognition system during operation of the controller for the shared space air treatment apparatus.

6. The controller according to claim 1, wherein the store of data is held in an external store accessible from the controller.

7. The controller according to claim 1, wherein the at least one sensor comprises an infrared temperature sensor and the first transceiver is operable to receive an air characteristic value local to the said person comprising an air temperature value.

8. The controller according to claim 1, wherein the at least one sensor comprises an air humidity sensor and the first transceiver is operable to receive an air characteristic value local to the said person comprising an air humidity value.

9. The controller according to claim 1 in electronic communication with a further controller in a different location, and wherein the stored air characteristic value for the said person is passed from the controller to the further controller when the said person moves to the different location.

10. The controller according to claim 1, wherein the transceiver is operable, in an absence of stored recognition and stored air characteristic data for the said person, to interrogate the recognition system for any gathered characteristic data for the said person, and to send at least one adjustment instruction to adjust the air supply outlet according to the gathered characteristic data for the said person.

11. A method of operating a controller for a shared space air treatment apparatus, comprising:using a recognition system to identify the presence of a person at a location associated with an air treatment zone of the shared space air treatment apparatus;comparing, by a comparator, a stored air characteristic value associated with the said person and a sensed air characteristic associated with the zone; andsending, by a transceiver, at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

12. The method according to claim 11, wherein using the recognition system comprises using a facial recognition machine learning and inferencing system.

13. The method according to claim 11, further comprising modifying the store of data according to new data for the said person learned by the recognition system during operation of the controller for the shared space air treatment apparatus.

14. The method according to claim 11, further comprising electronically communicating with a further controller in a different location, and passing the stored air characteristic value for the said person from the controller to the further controller when the said person moves to the different location.

15. The method according to claim 11, further comprising, in an absence of stored recognition and stored air characteristic data for the said person, interrogating the recognition system for any gathered characteristic data for the said person, and sending at least one adjustment instruction to adjust the air supply outlet according to the gathered characteristic data for the said person.

16. A computer program product comprising a non-transitory computer-readable storage medium having stored thereon instructions that when executed by a processor cause the computer processor to:use a recognition system to identify the presence of a person at a location associated with an air supply treatment zone of a shared space air treatment apparatus;compare a stored air characteristic value associated with the said person and a sensed air characteristic associated with the zone; andsend, by a transceiver, at least one adjustment instruction to adjust a target air characteristic value for the associated zone based on the comparison of the stored air characteristic value and the sensed air characteristic value.

17. The computer program product of claim 16, wherein using the recognition system comprises using a facial recognition machine learning and inferencing system.

18. The computer program product of claim 16, further comprising instructions to modify the store of data according to new data for the said person learned by the recognition system during operation of the controller for the shared space air treatment apparatus.

19. The computer program product of claim 16, further comprising instructions to electronically communicate with a further controller in a different location, and pass the stored air characteristic value for the said person from the controller to the further controller when the said person moves to the different location.

20. The computer program product of claim 16, further comprising instructions to, in an absence of stored recognition and stored air characteristic data for the said person, interrogate the recognition system for any gathered characteristic data for the said person, and send at least one adjustment instruction to adjust the air supply outlet according to the gathered characteristic data for the said person.

Images