Entrance system classification

Abstract

A computer-implemented method (100) for classifying an entrance system (10), the method (100) comprising: receiving (110), from a client device (310), a set of imagery (60) including at least two different portions of the entrance system (10); feeding (120) the set of imagery (60) to a machine learning model (64) trained on a dataset involving sets of imagery of predetermined entrance systems; determining (130) a classification (68) of said entrance system (10) based on estimation outputs (65) obtained from the machine learning model (64); and transmitting (140), to the client device (310), information pertaining to the classification (68) of said entrance system (10).

Description

[0001] ENTRANCE SYSTEM CLASSIFICATION

[0002] TECHNICAL FIELD

[0003] The present invention generally relates to the field of entrance systems. More specifically, the present invention relates to a computer-implemented method for classifying an entrance system. The present invention also relates to an associated computer-implemented method for obtaining a classification of an entrance system, a backend computing service, a computer program product and a non-transitory computer readable storage medium.

[0004] BACKGROUND

[0005] Servicing and installing entrance systems demands significant technical expertise due to the wide variety of door types and configurations. These include automatic overhead sectional doors, sliding doors, swing doors, and revolving doors, each with distinct mechanical and operational features. The absence of industry-wide standardization adds complexity, requiring technicians to be well acquainted to the unique specifications of various systems.

[0006] Misclassification of entrance systems can lead to ordering incorrect replacement parts, causing delays, increased costs, and customer dissatisfaction. Worse, installing incompatible components can compromise functionality, safety, and security, ultimately posing serious risks to users and property.

[0007] It is in view of the above-identified concerns and others that the present inventors have realized that there is room for improvements in this field.

[0008] SUMMARY

[0009] The challenges outlined in the background section, such as the diverse configurations of entrance systems and the lack of industry-wide standardization, indicate the complexity faced by service technicians in accurately classifying these systems for servicing and installation purposes. This complexity, accentuated by the risk of ordering incorrect replacement parts, emphasizes the need for a more systematic and reliable approach to entrance system classification. The present inventors have identified that leveraging advancements in machine learning technology could address these issues by providing a precise and efficient method for classifying entrance systems. By implementing approaches that utilize a machine learning model trained on imagery datasets of various entrance systems, it is possible to accurately determine the classification of an entrance system. This approach not only mitigates the risk of incorrect part orders but also enhances the overall safety and functionality of entrance installations by ensuring the compatibility of components, ultimately leading to improved user satisfaction and reduced costs.

[0010] In a first aspect of this disclosure there is accordingly provided a computer- implemented method for classifying an entrance system, the method comprising: receiving, from a client device, a set of imagery including at least two different portions of the entrance system; feeding the set of imagery to a machine learning model trained on a dataset involving sets of imagery of predetermined entrance systems; determining a classification of said entrance system based on estimation outputs obtained from the machine learning model; and transmitting, to the client device, information pertaining to the classification of said entrance system.

[0011] The first aspect utilizes a machine learning model trained on diverse imagery datasets to accurately classify entrance systems, thereby reducing incorrect part orders, enhancing safety and functionality, and ultimately improving user satisfaction and reducing costs.

[0012] In some embodiments, the method further comprises obtaining one or more spare part recommendations matching said classification of said entrance system. A technical benefit may include ensuring that the correct parts are readily available, reducing downtime and enhancing maintenance efficiency.

[0013] In some embodiments, the method further comprises sending a request for parts to a digital product store, the request involving the classification of said entrance system, wherein the digital product store returns said one or more spare part recommendations matching the requested classification. A technical benefit may include streamlining the parts ordering process, reducing human error, and expediting repairs.

[0014] In some embodiments, the spare part recommendations match portions of the entrance system included in the set of imagery. A technical benefit may include providing precise part matches that ensure compatibility and reduce the likelihood of installation errors.

[0015] In some embodiments, the spare part recommendations match portions of the entrance system not included in the set of imagery. A technical benefit may include offering comprehensive maintenance solutions by anticipating additional needs beyond the immediate scope.

[0016] In some embodiments, the spare part recommendations include a recommendation factor being one or more of an aging property, a compliance property, a material fatigue property, a corrosion property, an obsolescence property, a manufacturing defect property, an environmental condition property, a maintenance neglect property, and an operational stress property. A technical benefit may include providing insights that inform proactive maintenance and extend the lifespan of the entrance system.

[0017] In some embodiments, the method further comprises obtaining a maintenance manual matching the classification of said entrance system. A technical benefit may include facilitating accurate and efficient maintenance procedures, reducing the risk of errors.

[0018] In some embodiments, the method further comprises obtaining an initial confirmation prompt from the client device including a request to carry out the classifying of the entrance system. A technical benefit may include ensuring user engagement and validation before proceeding, enhancing data integrity.

[0019] In some embodiments, the method further comprises comparing the estimation outputs to a predefined limit value indicating a minimum match confidence, and determining the classification based on an outcome of said comparison. A technical benefit may include enhancing the reliability and accuracy of the classification process.

[0020] In some embodiments, the method further comprises requesting, to the client device, additional imagery input in response to the outcome of said comparison indicating an insufficient match. A technical benefit may include improving model accuracy by acquiring higher-quality data for analysis.

[0021] In some embodiments, the method further comprises preprocessing the set of imagery before feeding it to the machine learning model. A technical benefit may include improving image quality and consistency, which enhances model performance. In some embodiments, the method further comprises applying optical character recognition, OCR, to the set of imagery, wherein determining the classification is further based on outputs from said OCR. A technical benefit may include extracting additional text data that enriches the classification process.

[0022] In some embodiments, the set of imagery includes a front panel portion of a movable door member of the entrance system, a rear panel portion of the movable door member, and a hinge portion of a hinge mechanism of the movable door member. A technical benefit may include selecting some of the most important portions of an entrance system that can provide a comprehensive view installation, enhancing classification accuracy and reducing processing time.

[0023] In a second aspect, a computer-implemented method for obtaining a classification of an entrance system is provided, the method comprising: obtaining, using a client device, a set of imagery including at least two different portions of the entrance system; transmitting the set of imagery to a backend computing service, the backend computing service comprising a processor being configured to receive the set of imagery, feed the set of imagery to a machine learning model trained on a dataset involving sets of imagery of predetermined entrance systems, and determine a classification of said entrance system based on estimation outputs obtained from the machine learning model; and obtaining information pertaining to the classification of the entrance system from the backend computing service.

[0024] In a third aspect, a backend computing service is provided, comprising a processor configured to receive, from a client device, a set of imagery including at least two different portions of the entrance system; feed the set of imagery to a machine learning model trained on a dataset involving sets of imagery of predetermined entrance systems; determine a classification of said entrance system based on estimation outputs obtained from the machine learning model; and transmit, to the client device, information pertaining to the classification of said entrance system.

[0025] In a fourth aspect, a computer program product is provided, comprising computer code for performing the method according to the first aspect when the computer program code is executed by a processor of a backend computing service.

[0026] In a fifth aspect, a non-transitory computer readable storage medium is provided, having stored thereon a computer program comprising computer program code for performing the method according to the first aspect when the computer program code is executed by a processor of a backend computing service.

[0027] In a sixth aspect, a computer program product is provided, comprising computer code for performing the method according to the second aspect when the computer program code is executed by a processor of a client device.

[0028] In a seventh aspect, a non-transitory computer readable storage medium is provided, having stored thereon a computer program comprising computer program code for performing the method according to the second aspect when the computer program code is executed by a processor of a client device.

[0029] Embodiments of the invention are defined by the appended dependent claims and are further explained in the detailed description section as well as in the drawings.

[0030] It should be emphasized that the term “comprises / comprising” when used in this specification is taken to specify the presence of stated features, integers, steps, or components, but does not preclude the presence or addition of one or more other features, integers, steps, components, or groups thereof.

[0031] All terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / an / the [element, device, component, means, step, etc.]" are to be interpreted openly as referring to at least one instance of the element, device, component, means, step, etc., unless explicitly stated otherwise.

[0032] The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

[0033] BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Objects, features and advantages of embodiments of the invention will appear from the following detailed description, reference being made to the accompanying drawings.

[0035] FIG. 1 is a schematic illustration of an entrance system subjected to classification.

[0036] FIG. 2 is a schematic flowchart diagram depicting exemplary steps of a computer-implemented method for obtaining a classification of an entrance system. FIG. 3 is a schematic flowchart diagram depicting exemplary steps of a computer-implemented method for classifying an entrance system.

[0037] FIG. 4 is a flowchart diagram illustrating a computer-implemented method for classifying an entrance system.

[0038] FIG. 5 is a flowchart diagram illustrating a computer-implemented method for obtaining a classification of an entrance system.

[0039] FIG. 6 is a schematic illustration of a non-transitory computer-readable storage medium in one exemplary embodiment, capable of storing a computer program product.

[0040] DETAILED DESCRIPTION OF EMBODIMENTS

[0041] Embodiments of the invention will now be described with reference to the accompanying drawings. The invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and may convey the scope of the invention to those skilled in the art. The terminology used in the detailed description of the particular embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like numbers refer to like elements.

[0042] FIG. 1 is an exemplary visualization of an entrance system 10 subjected to classification. In this example the entrance system 10 is an overhead door system, although other exemplary entrance systems may involve revolving door systems, swing door systems, sliding door systems, or the like. The entrance system 10 includes a movable door member 12 having a door leaf 11. The door leaf 11 includes several front panel portions 11-1 and a rear panel portion 11-2. For visualization purposes, the front and rear panel portions 11-1, 11-2 are shown as two separate units, although it should be understood that these are parts of the same door leaf 11 but on opposite sides thereof. In addition, a hinge mechanism 18 is shown (zoomed in at a hinge portion 18-1) attached to the movable door member 12.

[0043] An authorized user 30 is operating a client device 310. The authorized user 30 may be a service personnel, technician, operator, or the like. The client device 310 may be a smartphone, smart tablet, PDA, laptop, smartwatch, AR glasses, or the like. The client device 310 includes an image capturing device capable of capturing one or more images of the surroundings. The image capturing device may be integrated with the client device 310, or alternatively provided external to the client device 310 and capable of communicating the image(s) with the client device 310 using any known communication standards. The client device 310 is an interactive device, meaning that the authorized user 30 can interact with the client device 310 for instructing it to capture one or more images of the surroundings. The client device 310 comprises a display screen configured to present visual information to the authorized user 30. The client device 310 may be configured to provide other feedback, such as sound, audio, haptics, etc., through suitable devices integrated with or external to the client device 310.

[0044] The client device 310 is configured to communicate with a backend computing service 300, here depicted as a cloud. The communication may be effected using any known communication technologies known in the art, including but not limited to short- range communication interfaces such as IEEE 802.11, IEEE 802.15, ZigBee, WirelessHART, WiFi, Bluetooth®, BLE, RFID, WLAN, MQTT loT, CoAP, DDS, NFC, AMQP, LoRaWAN, Z-Wave, Sigfox, Thread, EnOcean, mesh communication, other forms of proximity-based device-to-device radio communication signal such as LTE Direct, or long-range communication interfaces such as W-CDMA / HSPA, GSM, UTRAN, LTE or Starlink.

[0045] The backend computing service 300 may be implemented using any commonly known cloud-computing platform technologies, such as e.g. Amazon Web Services, Google Cloud Platform, Microsoft Azure, DigitalOcean, Oracle Cloud Infrastructure, IBM Bluemix or Alibaba Cloud. The backend computing service 300 may be included in a distributed cloud network that is widely and publically available, or alternatively limited to an enterprise. In alternative implementations, the backend computing service 300 may be locally managed as e.g. a centralized server unit.

[0046] The backend computing service 300 may be configured to maintain a storage device, being included with or external to the backend computing service 300. Connection to cloud storage means may be established using DBaaS (Database-as-a- service). For instance, cloud storage means may be deployed as a SQL data model such as MySQL, PostgreSQL or Oracle RDBMS. Alternatively, deployments based on NoSQL data models such as MongoDB, Amazon DynamoDB, Hadoop or Apache Cassandra may be used. DBaaS technologies are typically included as a service in the associated cloud-computing platform.

[0047] Server configurations other than cloud-based may be realized in other examples, for instance based on any type of client-server or peer-to-peer (P2P) architecture. Server configurations may thus involve any combination of e.g. web servers, database servers, email servers, web proxy servers, DNS servers, FTP servers, file servers, DHCP servers, to name a few.

[0048] The present inventors have realized that the objectives described herein can be achieved by way of providing a set of imagery including at least two different portions of the entrance system 10. A “set” of imagery shall be understood as including one or more images. Therefore, in some examples one single image in the set of imagery may include a plurality of portions of the entrance system 10. For example, a picture taken from afar may show both a hinge portion 18-1 and a front panel portion 11-1 of the movable door member 12. In other examples, the set of imagery includes two or more images, each image in the set of imagery including at least one portion of the entrance system 10. A “portion” shall be understood as an entire component, such as a hinge, or at least parts thereof, such as an upper / lower hinge plate including one or more sets of screw holes or openings.

[0049] In the particular example of FIG. 1, the set of imagery will include three images, each image showing a respective portion of the entrance system 10. More specifically, the set of imagery includes a first image of a front panel portion 11-1, a second image of a rear panel portion 11-2, and a third image of a hinge portion 18-1. While this is just an exemplary set of imagery, the present inventors have conducted studies that indicate that these three particular portions in some cases may be sufficient for classifying the entrance system 10 using approaches taught herein. Also, any number of images can be captured in any order. This is due to these three portions oftentimes being associated with unique appearances, or at least a distinctive appearance that is associated with fewer possible alternatives compared to other portions of the entrance system. In particular, these three portions in combination typically enable classification of most entrance systems currently on the market. For the panel portions 11-1, 11-2, this distinctive appearance can relate to patterns, colors, textures, carvings / engravings, glass inserts, hardware, number of panels, shapes, material contrast, and the like.

[0050] For the hinge portion 18-1, this distinctive appearance can relate to designs, shapes, finishes, coatings, materials, number of holes / plates, type of holes / plates, hole arrangements, plate configurations, sharp edges / round edges, ball bearings, and the like.

[0051] In other examples, similar or alternative unique or at least distinctive appearances can be envisaged for any of the other units / components / modules / etc., for which imagery can be captured. Such other units / components / modules / etc., may include automatic door operators, linkages, transmission types, sensory modules, electronic control units, handles, knobs, locksets, thresholds, windows, lights, door surroundings, architectural moldings, tracks, ventilation openings, emergency exit features, weather stripping and seals, and the like, each having a set involving one of more distinctive features.

[0052] In FIG. 2, a client device 310 is shown, operating in frontend contexts. The client device 310 is configured to obtain information pertaining to a classification of the entrance system 10. The process of obtaining classification information according to the teachings herein shall be understood as a continued and / or guided human-machine interaction process. The user operating the client device 310, such as the authorized user 30 as discussed above, will be assisted in performing the technical task of finding accurate replacement options for parts of the entrance system.

[0053] This particular computer program is named “PartFinder”, and includes, in addition to the classification, an additional step of obtaining one or more spare part recommendations matching the classification of the entrance system 10. In this example the PartFinder program involves an initial step, followed by a three-step continued and / or guided human-machine interaction process, followed by a computer backend determination of a classification of the entrance system 10. Other examples may include any number of steps in the guided human-machine interaction process, as this may generally be based upon how many images that are included in the set of imagery.

[0054] Before the guided interaction process is initiated, the authorized user 30 may prompt to confirm that the entrance system 10 indeed is not recognized (for example due to preemptive user knowledge), and that classification is necessary. Hence, this initial confirmation prompt includes a request to carry out the classifying of the entrance system 10, offering the authorized user greater flexibility in deciding when to take action. The initial confirmation prompt may be submitted via the client device 310 to the backend computing resource 300, optionally upon request by the backend computing resource 300.

[0055] In this example the authorized user 30 clicks a “NO” button which is a graphical design element, whereby the procedure continues to step one of the guided interaction process. There may be other suitable ways of providing the initial confirmation prompt, such as using a voice command interface that allows the user to verbally confirm the need for classification, deploying a separate physical device with a dedicated button for initiating the process, utilizing a touchscreen interface where users can swipe or tap to provide confirmation, integrating a gesture-based system that recognizes specific hand movements to proceed, employing a mobile app notification that prompts users to confirm through their smartphones, or implementing a QR code system where scanning the code on-site triggers the confirmation prompt.

[0056] In a first step of the guided interaction process, the client device 310 instructs the authorized user to take a picture of a front panel portion 11-1 of the entrance system 10, more specifically of the door leaf 11 of the movable door member 12. The client device 310 may continuously guide the user into capturing a sufficiently accurate representation of the front panel portion 11-1. The client device 310 may identify any potential issue with the captured image, such as poor lighting, wrong focus, too zoomed in or zoomed out, blurry view, and the like. The client device 310 may request that the authorized user 30 captures one or more additional images until the quality is sufficient for subsequent analysis, or from different perspectives, or from different distances to the front panel portion 11-1, etc.

[0057] In response to the client device 310 accepting the captured image(ry) with respect to one or more of the above considerations, a second step of the guided interaction process involves capturing a picture of a rear panel portion 11-2. This may involve similar considerations as for the first step.

[0058] In response to the client device 310 accepting the captured image(ry) with respect to one or more of the above considerations, a third step of the guided interaction process involves capturing a picture of a hinge portion 18-1. This may involve similar considerations as for the first and / or second steps.

[0059] After the completion of the guided interaction process, the remaining steps are functionally carried out by the backend computing service 300. The entrance system is accordingly classified, in this case with the type defined by code “es-123”.

[0060] As discussed above, the process may involve an additional step of obtaining one or more spart part recommendations that match the classification, in this case spare part(s) that is / are compatible with the code “es-123”. The client device 310 may feature a functionality to automatically order these parts (“Place order”), and optionally have them delivered to a location where the entrance system 10 is arranged. This may be reported automatically from the client device 310 to the digital product store.

[0061] FIG. 3 shows the client device 310 operating in frontend contexts. The client device 310 transmits a set of imagery 60 to the backend computing service 300, operating in backend contexts.

[0062] The first step is for the backend computing service 300 to receive a set of imagery 60 from the client device 310. The set of imagery 60 includes images of at least two portions of the entrance system, such as any two of the front panel portion, the rear panel portion, or the hinge portion.

[0063] The procedure then continues by feeding the set of imagery 60 to a machine learning model 64, which processes this set of imagery 60 to generate estimation outputs 65. The estimation outputs 65 serve to evaluate the likelihood that the images within the set of imagery 60 correspond to a previously recognized type of entrance system. The estimation outputs 65 may be represented as a probability distribution across a range of predefined entrance system categories, each representing a distinct system type that the model has been trained to classify. For example, a broad category might include automatic overhead sectional doors, sliding doors, swing doors, and revolving doors, among others. A more narrow category may then include, for example, overhead sectional doors used in residential buildings. An even narrower category may then include, for example, specific components that together make up the classification of the entrance system.

[0064] Each category in this distribution may be assigned a probability value, reflecting a confidence of the machine learning model 64 that the input set of imagery 60 belongs to that specific type of entrance system. For instance, if the set of imagery 60 predominantly features characteristics typically found in automatic overhead sectional doors, such as a segmented panel visible in the front and rear panel images, the model might assign a higher probability to the category of automatic overhead sectional doors.

[0065] As an example, the machine learning model 64 might output a distribution like this: 75% probability for automatic overhead sectional doors, 15% for sliding doors, 5% for swing doors, and 5% for revolving doors. The backend computing service 300 would then interpret these probabilities to determine that the entrance system is most likely an automatic overhead sectional door, based on the highest probability value. This probabilistic approach allows for flexible and nuanced classification, accommodating slight variations in design or appearance while still providing a robust decision-making framework. It ensures that even if the entrance system 10 exhibits atypical features, the machine learning model 64 can still produce a reliable classification by weighing the overall evidence presented in the set of imagery 60.

[0066] The machine learning model 64 may employ estimation techniques such as convolutional neural networks, to convert the raw pixel data into meaningful predictions. This may involve an initial representation of the set of imagery 60 as multidimensional arrays, with each pixel contributing to a numerical format. For RGB images, this can involve a three-dimensional array for the red, green, and blue channels. Preprocessing steps like normalization and resizing may be applied to standardize the input, enhancing computational efficiency. For example, the set of imagery 60 might be resized to 224x224 pixels to align with model requirements. The machine learning model 64 then performs feature extraction, identifying image features hierarchically. In a convolutional neural network, early layers might detect edges or textures, while deeper layers capture complex patterns like the shapes of door panels or hinges. Filters highlight spatial patterns, and pooling layers focus on critical information, refining the image representation.

[0067] Post-processing steps may be applied to refine the estimation outputs 65. Visualization tools, like heatmaps, may be generated that highlight image regions influencing the decision taken by the machine learning model 64 such that insights into its reasoning can be provided. The backend computing service 300 then determines a classification 68 of the entrance system based on the estimation outputs 65 obtained from the machine learning model 64.

[0068] In some scenarios, the backend computing service 300 may compare the classification 68 against a predefined limit value. The predefined limit value serves as a threshold for minimum match confidence, ensuring that the classification is considered reliable before it is finalized. For example, if the predefined limit value is set at 70%, the classification with 80% probability is deemed trustworthy and accepted.

[0069] Conversely, if the highest probability were only 65%, below the 70% threshold, the backend computing service 300 might flag the classification for further review or seek additional imagery to increase confidence. By incorporating this limit value, the backend computing service 300 can safeguard against an insufficient match in the outcome of the comparison, enhancing the overall reliability and accuracy of the classification process.

[0070] In some examples, an additional step of applying optical character recognition, OCR, to the set of imagery 60, may be carried out. The determination of the classification 68 is in this case further based on outputs from said OCR. This may be done utilizing OCR software integrated within the backend computing service 300 to extract text from images. Alternatively, a cloud-based OCR service may be deployed which processes the set of imagery 60 remotely and return text data. Yet alternatively, OCR capabilities may be provided directly within the client device 310 for immediate text extraction, for example using a built-in capability with the “PartFinder”-application that allow for on-site text recognition. The extracted text may provide additional information like serial numbers, manufacturer details, or model names that complement visual features, thus refining and supporting the classification process by offering another layer of data for analysis.

[0071] Information pertaining to the classification 68 is then transmitted to the client device 310, finalizing the procedure. This information typically includes an identified entrance system category (e.g., sliding door, swing door, etc.). Additionally, this information may encompass metadata that offers further context and utility to the classification. Such metadata could include the confidence level of the classification, indicating a certainty in its identification. Moreover, the metadata might detail any distinctive features or characteristics that were relevant in reaching the classification 68, such as unique design elements or components captured in the set of imagery 60. This could be supported by visual aids like annotated images or heatmaps highlighting these features.

[0072] In optional examples, the metadata could also provide recommendations for compatible spare parts, facilitating follow-up actions by the technician. To do so, the classification 68 may be provided as input to a digital product store 80 which returns one or more spare part recommendations 70 matching the classification 68. The digital product store 80 may be one of a web shop 81, a Product Information Management (PIM) system 82 or an Enterprise Resource Planning (ERP) system 83. The backend computing service 300 may thus automatically provide in the spare part recommendations 70 a quick and efficient way for the authorized user to place orders directly with a digital product store 80 through the client device 310.

[0073] In some examples, the spare part recommendations 70 correspond to the portions of the entrance system that were photographed and provided in the set of imagery 60. This allows for a direct replacement of the photographed portions of the entrance system.

[0074] In some examples, the spare part recommendations 70 correspond to portions of the entrance system that match the classification 68, but were not necessarily included in the set of imagery 60 provided to the backend computing service 300. This can be done due to the fact that certain parts of an entrance system are only compatible with other certain parts, or other reasons not necessarily pertaining to compatibility. Therefore, if a particular classification 68 is established based on imagery 60 of one or more first components of an entrance system, one or more second components different from said one or more first components can be included in the spare part recommendations 70. This enables a servicing and / or installation of a larger portion of the entrance system than what was originally photographed and supplied to the backend computing service 300 via the set of imagery 60.

[0075] In some examples, recommendation factors can be included in the spare part recommendations 70. These may include one or more of an aging property (e.g. how old a certain component is), a material fatigue property (e.g. whether there is a decline in structural integrity due to repeated stress / load-bearing activity), a corrosion property (e.g. if there is an exposure to moisture / air / corrosive substances), an obsolescence property (e.g. due to advancements in technology rendering certain components obsolete over time), a manufacturing defect property (e.g. inherent defects or weaknesses from the manufacturing process of components), an environmental condition property (e.g. extreme temperatures, humidity, exposure to contaminants), a maintenance neglect property (e.g. inadequate or irregular maintenance practices contributing to deterioration of components), and an operational stress property (e.g. components being subjected to heavy loads, high speeds or intense operating conditions so that wear is accelerated).

[0076] In view of the above and to further exemplify this, the spare part recommendations 70 may realize that certain components of that entrance system type as identified by metadata of the classification 68 no longer comply with compliance or safety standards, for example due to regulatory requirement changes. The spare part recommendations 70 may thus include a recommendation said replace certain components.

[0077] In some examples, the spare part recommendations 70 may include time stamp data indicating a time when the entrance system was previously serviced / installed, and accordingly a recommendation to replace certain outdated components.

[0078] In some examples, the spare part recommendations 70 may include locational data of certain regional or other standards that shall be complied with.

[0079] The process may involve an additional step of obtaining a maintenance manual that corresponds with the classification of the entrance system. Once the classification is determined, a request can be made to access a specific maintenance manual that aligns with the classification code, such as “es-123”. This manual provides detailed guidance tailored to the particular type of entrance system according to its classification, facilitating accurate maintenance procedures. The maintenance manual can be sourced from a digital product store, such as one of those discussed above. By ensuring that the maintenance manual is specifically matched to the entrance system type, the authorized user 30 is allowed to perform maintenance tasks with confidence and precision, adhering to the established protocols for that specific system. Furthermore, the client device 310 may include functionality to automatically download or access the relevant manual, ensuring that the necessary information is readily available to the user, thereby streamlining the maintenance process and enhancing the overall efficiency of service operations.

[0080] In addition or as an alternative to the spare part recommendations 70, the backend computing service 300 may provide a maintenance manual or possibly an installation guide that is based on the classification 68 of the entrance system. The maintenance manual 72 typically includes detailed instructions for regular upkeep and troubleshooting of the entrance system. The installation guide may provides step-by- step directions for correctly setting up and configuring the system components. The maintenance manual 72 and / or the installation guide may be supplied together with the spare part recommendations 70.

[0081] Delivering one or more of the spare part recommendations 70, the maintenance manual 72, and the installation guide, can be done through various methods. Such methods include delivering a digital document that can be viewed on the client device 310, providing access to an online portal where a manual or guide can be downloaded or accessed interactively, sending a direct email with the document attached for offline access, offering an in-app resource library within a mobile application for real-time retrieval, allowing users to scan a code that links to the specific manual or guide, or integrating with an augmented reality system that overlay instructions directly onto the entrance system in the user’s field of view.

[0082] FIG. 4 shows a computer-implemented method 100 for classifying an entrance system 10. The method 100 is implemented by the backend computing service 300. The method 100 comprises a step 110 of receiving, from the client device 310, a set of imagery 60 including at least two different portions of the entrance system 10. The method 100 further comprises a step 120 of feeding the set of imagery 60 to a machine learning model 64 trained on a dataset involving sets of imagery of predetermined entrance systems. The method 100 further comprises a step 130 of determining a classification 68 of the entrance system based on estimation outputs 65 obtained from the machine learning model 64. The method 100 further comprises a step 140 of transmitting, to the client device 310, information pertaining to the classification of the entrance system 10.

[0083] FIG. 5 shows a computer-implemented method 200 for obtaining a classification 68 of an entrance system 10. The method 200 is implemented by a client device 310. The method 200 comprises a step 210 of obtaining, using the client device 310, a set of imagery 60 including at least two different portions of the entrance system 10. The method 200 further comprises a step 220 of transmitting the set of imagery 60 to a backend computing service 300 comprising a processor being configured to perform a set of actions. These actions involve receiving the set of imagery 60, feeding the set of imagery 60 to a machine learning model 64 trained on a dataset involving sets of imagery of predetermined entrance systems, and determining a classification 68 of the entrance system 10 based on estimation outputs 65 obtained from the machine learning model 64. The method 200 further comprises a step 230 of obtaining information pertaining to the classification 68 of the entrance system 10 from the backend computing service 300.

[0084] FIG. 6 is a schematic illustration of a non-transitory computer-readable storage medium 400 in one exemplary embodiment, capable of storing a computer program product 410. The non-transitory computer-readable storage medium 400 in the disclosed embodiment is a memory stick, such as a Universal Serial Bus (USB) stick; the non- transitory computer-readable storage medium 400 may however be embodied in various other ways instead, as is well known per se to the skilled person. The USB stick 400 comprises a housing 430 having an interface, such as a connector 440, and a memory chip 420. In the disclosed embodiment, the memory chip 420 is a flash memory, i.e. a non-volatile data storage that can be electrically erased and re-programmed.

[0085] The memory chip 420 stores the computer program product 410 which is programmed with computer program code (instructions) that when loaded into and executed by a processing device, such as a CPU, will perform either the method 100 or the method 200 as described herein, and optionally any of their respective embodiments or examples as described herein. The USB stick 400 is arranged to be connected to and read by a reading device for loading the instructions into the processing device. The processing device may, for instance, be comprised in the client device 310 or in the backend computing service 300.

[0086] It should be noted that a computer-readable medium can also be other mediums such as compact discs, digital video discs, hard drives or other memory technologies commonly used. The computer program code (instructions) can also be downloaded from the computer-readable medium via a wireless interface to be loaded into the processing device.

[0087] The invention has been described above in detail with reference to embodiments thereof. However, as is readily understood by those skilled in the art, other embodiments are equally possible within the scope of the present invention, as defined by the appended claims.

Claims

CLAIMS1. A computer-implemented method (100) for classifying an entrance system (10), the method (100) comprising: receiving (110), from a client device (310), a set of imagery (60) including at least two different portions of the entrance system (10); feeding (120) the set of imagery (60) to a machine learning model (64) trained on a dataset involving sets of imagery of predetermined entrance systems; determining (130) a classification (68) of said entrance system (10) based on estimation outputs (65) obtained from the machine learning model (64); and transmitting (140), to the client device (310), information pertaining to the classification (68) of said entrance system (10).

2. The method (100) of claim 1, further comprising obtaining one or more spare part recommendations (70) matching said classification (68) of said entrance system (10).

3. The method (100) of claim 2, further comprising sending a request for parts to a digital product store (80), the request involving the classification (68) of said entrance system (10), wherein the digital product store (80) returns said one or more spare part recommendations (70) matching the requested classification (68).

4. The method (100) of any of claims 2-3, wherein the spare part recommendations (70) match portions of the entrance system (10) included in the set of imagery (60).

5. The method (100) of any of claims 2-4, wherein the spare part recommendations (70) match portions of the entrance system (10) not included in the set of imagery (60).

6. The method (100) of any of claims 2-5, wherein the spare part recommendations (70) include a recommendation factor being one or more of an agingproperty, a compliance property, a material fatigue property, a corrosion property, an obsolescence property, a manufacturing defect property, an environmental condition property, a maintenance neglect property, and an operational stress property.

7. The method (100) of any preceding claim, further comprising obtaining a maintenance manual (72) matching the classification (68) of said entrance system (10).

8. The method (100) of any preceding claim, further comprising obtaining an initial confirmation prompt from the client device (310) including a request to carry out the classifying of the entrance system (10).

9. The method (100) of any preceding claim, further comprising comparing the estimation outputs (65) to a predefined limit value indicating a minimum match confidence, and determine the classification (68) based on an outcome of said comparison.

10. The method (100) of claim 9, further comprising requesting, to the client device (310), additional imagery input in response to the outcome of said comparison indicating an insufficient match.

11. The method (100) of any preceding claim, further comprising preprocessing the set of imagery (60) before feeding it to the machine learning model (64).

12. The method (100) of any preceding claim, further comprising applying optical character recognition, OCR, to the set of imagery (60), wherein determining (130) the classification (68) is further based outputs from said OCR.

13. The method (100) of any preceding claim, wherein the set of imagery (60) includes a front panel portion (11-1) of a movable door member (12) of the entrance system (10), a rear panel portion (11-2) of the movable door member (12), and a hinge portion (18-1) of a hinge mechanism (18) of the movable door member (16).

14. A computer-implemented method (200) for obtaining a classification (68) of an entrance system (10), the method (200) comprising: obtaining (210), using a client device (310), a set of imagery (60) including at least two different portions of the entrance system (10); transmitting (220) the set of imagery (60) to a backend computing service (300), the backend computing service (300) comprising a processor being configured to:- receive the set of imagery (60),- feed the set of imagery (60) to a machine learning model (64) trained on a dataset involving sets of imagery of predetermined entrance systems, and determine a classification (68) of said entrance system (10) based on estimation outputs (65) obtained from the machine learning model (64); and obtaining (230) information pertaining to the classification (68) of the entrance system (10) from the backend computing service (300).

15. A backend computing service (300) comprising a processor configured to: receive, from a client device (310), a set of imagery (60) including at least two different portions of the entrance system (10); feed the set of imagery (60) to a machine learning model (64) trained on a dataset involving sets of imagery of predetermined entrance systems; determine a classification (68) of said entrance system (10) based on estimation outputs (65) obtained from the machine learning model (64); and transmit, to the client device (310), information pertaining to the classification (68) of said entrance system (10).

16. A computer program product comprising computer code for performing the method (100) according to claim 1 when the computer program code is executed by a processor of a backend computing service (300).

17. A non-transitory computer readable storage medium having stored thereon a computer program comprising computer program code for performing the method(100) according to claim 1 when the computer program code is executed by a processor of a backend computing service (300).

18. A computer program product comprising computer code for performing the method (100) according to claim 14 when the computer program code is executed by a processor of a client device (310).

19. A non-transitory computer readable storage medium having stored thereon a computer program comprising computer program code for performing the method (100) according to claim 14 when the computer program code is executed by a processor of a client device (310).

Images