Plug-in generation method, electronic equipment, storage medium and computer program product

Abstract

The invention provides a plug-in generation method, electronic equipment, a storage medium and a computer program product, and relates to the technical field of terminals. According to the specific implementation scheme, in response to detected information meeting a plug-in generation condition, inquiry information is generated at least based on current scene information; sending the inquiry information to a pre-trained large model, and obtaining response information which corresponds to the inquiry information and is returned by the large model by taking a user operation log as response background knowledge; and selecting an atomic component corresponding to the plug-in function from a functional component library of each application program based on the response information, and generating a plug-in matched with the current scene by using the atomic component. According to the technical scheme provided by the invention, the plug-in function which better meets the personalized requirements of the user in the current scene can be provided by utilizing the prediction capability of the large model, the function use steps of the user are simplified, and the use experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a plug-in generation method, electronic device, storage medium and computer program product. Background Art

[0002] Functional service plug-ins can directly display the in-application information that users frequently pay attention to or the in-application functions that they frequently use on the desktop, providing users with a convenient way to view such information or use such functions, thereby improving efficiency. At the same time, it can also improve the aesthetics of the user's desktop and enrich the playability of the user's desktop. Currently, functional service plug-ins are basically fixed-type plug-in functions developed by application developers in accordance with the technical specifications of the corresponding system, and users need to manually add them to the desktop from the system's plug-in management service. Summary of the invention

[0003] Embodiments of the present application provide a plug-in generation method, an electronic device, a computer-readable storage medium, and a computer program product to alleviate or solve one or more technical problems existing in the prior art.

[0004] In a first aspect, an embodiment of the present application provides a plug-in generation method, which is applied to a terminal device, comprising: in response to detecting information that meets the plug-in generation condition, generating query information based on at least current scene information; wherein the information that meets the plug-in generation condition includes preset scene information and / or preset operation information, and the current scene information includes at least one of time, location type, weather, network connection status, device power, and user motion status;

[0005] The query information is sent to a pre-trained large model, and the response information corresponding to the query information is returned by the large model using the user operation log as the response background knowledge; wherein the user operation log records the user's historical use of the functions provided by each application in the terminal device, each use record contains the used function information and the use scenario information, and the response information includes at least one plug-in function generated by the large model that matches the current scenario;

[0006] Based on the response information, an atomic component corresponding to the plug-in function is selected from the functional component library of each application program, and a plug-in matching the current scenario is generated using the atomic component.

[0007] In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, and the processor implements any method of the embodiment of the present application when executing the computer program.

[0008] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any method of the embodiment of the present application is implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements any method of the embodiments of the present application when executed by a processor.

[0010] Based on the method of the embodiment of the present application, the predictive ability of the large model can be used to provide plug-in functions that are more in line with the user's personalized needs in the current scenario, simplify the user's function usage steps, and improve the user experience.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0013] Figure 1 is a schematic diagram of an exemplary hardware structure according to an embodiment of the present application;

[0014] Figure 2 is a flowchart of a plug-in generation method according to an embodiment of the present application;

[0015] Figure 3 is a schematic diagram comparing the display effects of plug-ins according to an embodiment of the present application;

[0016] Figure 4 is a schematic diagram of a plug-in generating device according to an embodiment of the present application;

[0017] Figure 5 It is a block diagram of an electronic device used to implement the method in the embodiment of the present application. DETAILED DESCRIPTION

[0018] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0019] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the related technologies of the embodiments of the present application. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0020] The functional service plug-ins provided by terminal devices currently on the market, such as mobile phones, tablets and wearable devices, often rely on fixed plug-in functions developed by the developers of each application based on the technical specifications of the system used by the device, such as the "Today's Weather", "Multi-day Weather" and "Air Quality" plug-in functions provided by the weather APP in the system application, or the "Scan" and "Payment and Collection" plug-in functions provided by Alipay in third-party applications, and the "Weibo Hot Search" plug-in function provided by Weibo. These applications that support plug-in functions generally provide their own plug-in-supported functions to the system's plug-in management service after successful installation.

[0021] Terminal devices usually display only a few functions that are frequently used by most users in the form of plug-ins on the user's desktop by default. Therefore, the functional service plug-ins displayed on the user's desktop by default are poorly matched with individual users. Users need to search for system applications or third-party applications in the system's plug-in management service to provide plug-in functions that meet their personal needs, and manually add them to the desktop for use. Moreover, users may need to use different applications and functions in different scenarios. If the user's desktop is not configured to display the corresponding plug-in function, the user needs to select the corresponding application in the application library and then find and use specific functions in the application interface, resulting in insufficient convenience.

[0022] In addition, since the systems used by terminal devices of different brands may be different and the screen ratios of different models of devices of the same brand may also be different, and the plug-in functions provided by third-party applications are developed and designed by the developers of third-party applications, the plug-in functions provided by third-party applications to the plug-in management service have a fixed plug-in framework, resulting in poor compatibility between the plug-in functions provided by third-party applications and the user desktop of the device, and problems such as inconsistent display or non-standard formatting may occur on different devices.

[0023] Based on this, the present application provides a plug-in generation method, which can construct a query mechanism to generate query information based on current scenario information (used to enable the big model to predict the user's intention to use each application and its functions in the system), and send the query information to the big model. The big model can access the user operation log of the terminal device through the application programming interface (Application Programming Interface, API), and generate response information corresponding to the query information using the user operation log as the response background knowledge, so that after obtaining the response information, the terminal device can select a plug-in function that better meets the user's personalized needs in the current scenario based on the response information and generate a functional service plug-in displayed on the user's desktop.

[0024] Specifically, existing terminal devices often collect and record user operation behaviors (including user use of applications, viewing various information in applications, and using various functions in applications), and simultaneously record basic scene information such as the time when the behavior occurs to form a user operation log. The user operation log mentioned in the embodiment of the present application can be configured to simultaneously record richer scene information (including but not limited to usage time, usage location, usage location type, weather conditions, working days / holidays, Bluetooth, Wi-Fi, motion status, etc.) when recording the user's operation behavior, so that the large model can more accurately predict the user's functional use intention based on the current scene information in the inquiry information when using the user operation log as the response background knowledge, so that the terminal device can display the corresponding plug-in function on the user's desktop in different scenarios. Functional service plug-ins constituted by plug-in functions simplify the user's function use steps and improve the user's use experience.

[0025] Among them, large models, also known as large language models (LLM), refer to natural language processing (NLP) models with huge parameter volumes and large amounts of training data. These models are usually built using deep learning technology and trained on large data sets in order to grasp the complexity and nuances of language so that they can perform various natural language processing tasks. Large language models can be GPT (Generative Pre-trained Transformer) series, such as GPT-3, GPT-4 and other models, BERT (Bidirectional Encoder Representations from Transformers) series models, ERNIE (a language model optimized for Chinese and other Asian languages) models, or T5 (a unified text-to-text pre-trained model that can perform a variety of NLP tasks) models, etc.

[0026] The plug-in generation method provided in the embodiments of the present application can be applied to electronic devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), and can also be applied to databases, servers, and terminal artificial intelligence-based service response systems. The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

[0027] For example, the electronic device may be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on a wireless system and a next generation communication system, such as a mobile terminal in a 5G network, a mobile terminal in a future evolved Public Land Mobile Network (PLMN) or a mobile terminal in a future evolved Non-terrestrial Network (NTN), etc.

[0028] As an example but not limitation, when the electronic device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as gloves, watches, AR (Augmented Reality) head-mounted display devices, VR (Virtual Reality) head-mounted display devices, or MR (Mixed Reality) head-mounted display devices, etc., which are equipped with long-distance communication modules and / or short-distance communication modules.

[0029] In some embodiments, the electronic device may be a device having Figure 1 The exemplary hardware structure of the exemplary mobile phone 100 shown in FIG. Figure 1As shown, the mobile phone 100 may specifically include: a radio frequency (RF) circuit 110, a memory 120, an input unit 130, a display unit 140, a sensor 150, an audio circuit 160, a short-range wireless communication module 170, a processor 180, and a power supply 190. Those skilled in the art will appreciate that Figure 1 The structure of the mobile phone 100 shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0030] Combine the following Figure 1 The components of the mobile phone 100 are described in detail:

[0031] The RF circuit 110 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 180 for processing; in addition, the data related to the uplink is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the RF circuit 110 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, and the wireless communication can include Global System For Mobile Communications (Global System For Mobile Communications, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Time Division Code Division Multiple Access (Time-Division Code Division Multiple Access, TD-SCDMA), Long Term Evolution (Long Term Evolution, LTE), New Radio (New Radio, NR), GNSS, FM, low-orbit satellite connection and / or IR technology, etc. The GNSS may include a Global Positioning System (GPS), a Global Navigation Satellite System (GLONASS), a BeiDou Navigation Satellite System (BDS), a Quasi-Zenith Satellite System (QZSS) and / or a Satellite Based Augmentation System (SBAS), etc.

[0032] The memory 120 can be used to store software programs and modules. The processor 180 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 120. The memory 120 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as pictures, audio data, phone books, etc.), etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Specifically, the memory 120 may store pictures taken by an electronic device or downloaded via a wireless network.

[0033] The input unit 130 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone 100. Specifically, the input unit 130 may include a touch panel 131 and other input devices 132. The touch panel 131, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 131 or near the touch panel 131 using any suitable object or accessory such as a finger (such as a single finger or multiple fingers), a stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 131 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 180, and can receive and execute the command sent by the processor 180. In addition, the touch panel 131 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 131, the input unit 130 may also include other input devices 132. Specifically, other input devices 132 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc.

[0034] The display unit 140 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 140 may include a display panel 141. Optionally, the display panel 141 may be configured in the form of a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), an active-matrix organic light emitting diode (AMOLED), etc. Further, the touch panel 131 may cover the display panel 141. When the touch panel 131 detects a touch operation on or near it, it is transmitted to the processor 180 to determine the type of touch event. Subsequently, the processor 180 provides a corresponding visual output on the display panel 141 according to the type of touch event. Although in Figure 1 In the embodiment, the touch panel 131 and the display panel 141 are two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 131 and the display panel 141 can be integrated to realize the input and output functions of the mobile phone. In at least one embodiment, the display panel 141 can be configured to display the wallpaper or dynamic wallpaper described in any embodiment of the present application.

[0035] The mobile phone 100 may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 141 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 141 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0036] The audio circuit 160, the speaker 161, and the microphone 162 can provide an audio interface between the user and the mobile phone. The audio circuit 160 can transmit the received audio data to the speaker 161 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, which is received by the audio circuit 160 and converted into audio data, and then the audio data is output to the processor 180 for processing, and then sent to another electronic device through the RF circuit 110, or the audio data is output to the memory 120 for further processing.

[0037] Communication technologies such as Wi-Fi, Bluetooth, Near Field Communication (NFC) and Ultra Wide Band (UWB) belong to short-range wireless transmission technologies. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the short-range wireless module 170, which provides users with wireless broadband Internet access. The above-mentioned short-range wireless module 170 may include a Wi-Fi chip, a Bluetooth chip, an NFC chip and a UWB chip. Through the Wi-Fi chip, the mobile phone 100 can achieve the function of Wi-Fi Direct connection with other electronic devices, and can also make the mobile phone 100 work in an AP mode (Access Point mode) that can provide wireless access services and allow other wireless devices to access, or work in a STA mode (Station mode) that can connect to an AP but does not accept wireless devices to access, thereby establishing point-to-point communication between the mobile phone 100 and other Wi-Fi devices.

[0038] The processor 180 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 120, and calling data stored in the memory 120, it executes various functions of the mobile phone and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor 180 may include one or more processing units; optionally, the processor 180 may include, for example, an application processor (Application Processor, AP), a modem processor, a graphics processor (Graphics Processing Unit, GPU), an image signal processor (Image Signal Processor, ISP), a controller, a video codec, a digital signal processor (Digital Signal Processor, DSP), a baseband processor, and / or a neural network processor (Neural-Network Processing Unit, NPU), etc. Among them, different processing units can be independent devices or integrated in one or more processors.

[0039] The mobile phone 100 also includes a power source 190 (such as a battery) for supplying power to various components. Preferably, the power source can be logically connected to the processor 180 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0040] The mobile phone 100 may also include a camera. Optionally, the position of the camera on the mobile phone may be front-mounted or rear-mounted, which is not limited in the embodiments of the present application. In at least one embodiment, the mobile phone may collect a scene image of the current scene through the camera, and determine the scene information and the scene type by parsing the scene image.

[0041] Figure 2 : is a flow chart of a plug-in generation method according to an embodiment of the present application, which can be applied to the aforementioned various terminal devices. The method includes:

[0042] Step S210, in response to detecting information that meets the plug-in generation condition, generating query information based on at least current scene information; wherein the information that meets the plug-in generation condition includes preset scene information and / or preset operation information, and the current scene information includes at least one of time, location type, weather, network connection status, device power, and user motion status;

[0043] Here, the plug-in functions corresponding to the function service plug-ins (hereinafter referred to as plug-ins) displayed by default on the user's desktop under normal circumstances are often the functions commonly used by most users configured by the system, or the plug-in functions manually selected by the user from the system's plug-in management service to be added to the user's desktop. Therefore, in order to maintain the display of the original plug-in functions in non-special scenarios, it is necessary to set certain trigger conditions. Only when the trigger conditions are detected, the plug-in generation method of the embodiment of the present application is executed, which can also avoid the terminal device frequently interacting with the large model to generate new plug-ins, resulting in additional consumption of power and network resources. The plug-in generation condition can also be understood as a trigger condition for generating query information or a trigger condition for executing the plug-in generation method.

[0044] The following are three types of plug-in generation conditions of the embodiment of the present application:

[0045] Plugin generation condition 1 (triggering plugin generation based only on scene information)

[0046] That is, when the preset scene information (including scene information combination) is detected, it is determined to meet the plug-in generation conditions, triggering the generation of inquiry information. For example, if the scene information is detected to include "the time is within the user's off-get off work time range" and "the location is the user's office location", in this case, the user may need to take a taxi to commute, take public transportation (buses and subways), scan a code to commute on a shared bicycle, etc.; if the scene information is detected to include "the location type is a food pedestrian street", in this case, the user may have a need for group buying services provided by applications such as "Dianping" and "Meituan"; therefore, after detecting this type of scene information, it can be determined to meet the plug-in generation conditions based solely on the scene information.

[0047] Exemplarily, in the case where plug-in generation is triggered based only on scenario information, in order to enable the large model to more accurately predict the user's functional usage intention, it is also necessary to obtain other scenario information other than the triggering scenario information, so that the richer scenario information in the query information can assist the prediction of the large model. In this case, after responding to detecting information that meets the plug-in generation conditions in step S210, it also includes:

[0048] In response to detecting that the information meeting the plug-in generation condition includes preset scene information, other scene information required for generating the query information is acquired; and the preset scene information and other scene information are used as current scene information.

[0049] For example, when it is detected that the scene information includes "the time is within the user's off-get off work time range" and "the location is the user's office location", and it is judged to meet the plug-in generation conditions, other scene information such as weather conditions can also be obtained. If the weather conditions are rainy or snowy, after obtaining the scene information, the big model may predict that the user has the need to take a taxi to commute, take public transportation (bus, subway), etc., but will not predict the user's need to scan a code to commute on a shared bicycle, etc.

[0050] Plugin generation condition 2 (triggering plugin generation based only on user operation information)

[0051] Compared with the plug-in generation condition 1, when the preset scene information is detected, it is determined that the plug-in generation condition is met, the plug-in generation condition can also be triggered only when the user's preset operation information on the device is detected.

[0052] Exemplarily, the preset operation information may include operation information for a preset function in the terminal device. In this case, in step S210, in response to detecting information that meets the plug-in generation conditions, query information is generated based at least on the current scene information, including: in response to detecting that the information that meets the plug-in generation conditions includes the preset operation information, query information is generated based on the current scene information and the preset operation information.

[0053] For example, if the preset operation information is "unlock the phone", when it is detected that the user has unlocked the phone, it is judged that the user has the need to use applications and functions, and meets the plug-in generation conditions. Then, based on the collected current scene information, such as "the location type is a food pedestrian street", query information can be generated and sent to the big model to enable the big model to predict the user's functional use intention. If the preset operation information is "turn off the alarm clock", the detected current scene information includes "weekdays and the time is within the working hours range". In this case, the user may be about to get up and go to work, and have the need to commute by public transportation, etc., the preset operation information and current scene information can be combined to generate query information and send it to the big model to enable the big model to predict the user's functional use intention.

[0054] Exemplarily, the preset operation information may also include plug-in function description information input by the user. In this case, in step S210, in response to detecting information that meets the plug-in generation conditions, query information is generated based at least on the current scene information, including: in response to detecting that the information that meets the plug-in generation conditions includes the preset operation information, extracting the plug-in function description information input by the user; generating query information based on the current scene information and the plug-in function description information.

[0055] Here, the user can describe the required plug-in function through the plug-in description interface provided by the system's plug-in management service or directly through voice input. For example, if the plug-in function description information is "add a service for purchasing vegetables", the query information can be generated directly based on the plug-in function description information. The big model can select one or several grocery shopping functions provided by "Meituan", "Ele.me", "Hema", etc. as the plug-in functions that the user wants to add through the query information and analysis of user operation logs. For example, if the plug-in function description information is "add a commuting service", the query information can be generated based on the plug-in function description information and the acquired weather type and other scene information and sent to the big model, so that the big model can predict the user's function usage intention, and finally display one or several commuting functions suitable for the current weather type on the device user's desktop as a plug-in type.

[0056] Plugin generation condition three (comprehensive scene information and user operation information trigger plugin generation)

[0057] Based on the above two plug-in generation conditions, more complex plug-in generation conditions can be set based on actual needs. For example, plug-in generation is triggered when both scene information and user operation information are met at the same time, so as to avoid the terminal device frequently interacting with the large model to generate new plug-ins and affecting the convenient use of the original plug-in functions.

[0058] For example, in the first plug-in generation condition, when the scenario information is detected to include "working hours and at home", plug-in generation will be triggered, and commuting-related plug-in functions will be generated and displayed on the user's desktop based on the prediction of the large model. In the second plug-in generation condition, when the user operation information is detected to be "turn off the alarm clock", plug-in generation will be triggered and commuting-related plug-in functions will be generated and displayed on the user's desktop based on the prediction of the large model. The third plug-in generation condition can be set to require that the scenario information includes "working hours and at home" and the user operation information is "turn off the alarm clock" or "unlock the phone" as the triggering conditions for plug-in generation, thereby reducing the possibility of misjudging the user's demand for plug-in use.

[0059] According to the method of this embodiment, a variety of plug-in generation conditions are set. These plug-in generation conditions can be configured to take effect separately or together without conflict according to actual needs to control plug-in generation, thereby more intelligently providing plug-in functions that better meet the user's current needs on the user desktop, and avoiding the terminal device frequently interacting with the large model to generate new plug-ins, resulting in additional consumption of power and network resources.

[0060] Step S220, sending the query information to the pre-trained big model, and obtaining the response information corresponding to the query information returned by the big model using the user operation log as the response background knowledge; wherein the user operation log records the user's historical usage records of the functions provided by each application in the terminal device, each usage record contains the used function information and usage scenario information, and the response information includes at least one plug-in function generated by the big model that matches the current scenario.

[0061] The user operation log here refers to the user's historical operation behavior recorded by the terminal device mentioned above. When recording the user's operation behavior (including the user's use of applications, viewing various information within the application, and using various functions within the application), the scene information that can be collected at the time of the historical operation behavior is also recorded synchronously (such as usage time, usage location, usage location type, weather conditions, weekdays / holidays, Bluetooth, Wi-Fi, exercise status, etc.). In this way, the large model can analyze the historical usage records of the functions provided by each application in the user operation log, and predict the user's function usage intention based on the user operation information provided by the query information and / or the current scene information.

[0062] The large model uses the user operation log as the response background knowledge, which can also be understood as using the user operation log as the plug-in knowledge base of the large model. The large model can access the user operation log based on the function call interface. In step S220, the query information is sent to the pre-trained large model, and the response information corresponding to the query information returned by the large model using the user operation log as the response background knowledge is obtained, including: sending the query information and the user identifier to the pre-trained large model, and obtaining the response information corresponding to the query information returned by the large model using the user operation log corresponding to the user identifier as the response background knowledge.

[0063] It is understandable that the operation of the big model requires a lot of computing resource support. The big model is often mounted on a cloud server, and the terminal device needs to interact with the big model through network requests. The user operation logs recorded by each terminal device are different, and the same terminal device may be used by two or more users. After receiving the query information, the big model also needs to access the corresponding user operation log to assist in predicting the user's functional usage intention. Therefore, when the terminal device sends the query information to the big model, it can also carry the user ID at the same time, so that the big model can access the corresponding user operation log based on the user ID through the function call interface provided by the corresponding terminal device.

[0064] Optionally, the large model may also be directly deployed on the terminal device. In this case, the large model can directly access the user operation log of the device without providing an additional user ID when sending the query information.

[0065] One beneficial effect of deploying large models on terminal devices is that since the calculation of the large model is performed locally, the interaction time is greatly shortened compared to the network-based interaction between the terminal device and the large model, thereby significantly reducing the response delay of the large model, allowing the terminal device to generate plug-ins more quickly to provide users with plug-in functions suitable for the current scenario, and can also be used for offline plug-in functions that predict user needs in some offline scenarios; another beneficial effect is that data such as user operation information involved in the inquiry information will not be transmitted to the cloud server for processing, which can better protect user privacy and improve security.

[0066] In practical applications, the large model can be deployed on the cloud or terminal device by comprehensively considering the computing resources of individual terminal devices, the privacy and security requirements of users, the speed and cost of plug-in function generation, and other dimensions. A hybrid deployment method can also be adopted to place the preprocessing and partial processing of the large model on the terminal device for execution, and distribute complex model reasoning and training to the cloud for execution, thereby taking into account the privacy and security requirements of users and the requirements of optimizing performance and reducing latency. Both of them are suitable for executing the plug-in generation method of the embodiments of the present application.

[0067] Exemplarily, the query information sent by the terminal device to the large model may be:

[0068] {"action":[{"abilityName":"Turn off the alarm","value":"06:30 legal working day"}],"conditionList":[{"status":{"abilityName":"Time","statusValue":"06:30"}},{"status":{"abilityName":"Location","statusValue":"Haidian District, Beijing"}},{"status":{"abilityName":"Location Type","statusValue":"Home"}},{"status":{"abilityName":"wifi","statusValue":" ue":"connected"}},{"status":{"abilityName":"Is it a working day","statusValue":"Yes"}},{"status":{"abilityName":"Bluetooth","statusValue":"Not connected"}},{"status":{"abilityName":"Weather","statusValue":"Raining during the day"}},{"status":{"abilityName":"Movement status","statusValue":"Standing"}},{"status":{"abilityName":"Device battery","statusValue":"37%"}}]}

[0069] The response information returned by the large model combined with the user operation log can be:

[0070] {"actionList":[{"action":{"appName":"Weather","statusValue":"Today's Weather"}},{"action":{"appName":"Wall Street News","statusValue":"News"}},{"action":{"appName":"AutoNavi Map","statusValue":"Directions to the Company"}}]}

[0071] In this example, the user turns off the alarm at 6:30 in the morning. The terminal device provides the operation information as well as scene information such as time, location (location type), WIFI and Bluetooth connection status, weather, motion status and device power to the big model. The big model predicts that the user may need to use the "Today's Weather Information" provided by the "Weather" application, the "Breaking News" function provided by the "Wall Street Journal" application, and the "Route to the Company" function provided by the "AutoNavi Map" application.

[0072] In another example, the query information sent by the terminal device to the large model may be:

[0073] {"action":[{"abilityName":" Unlock phone","value":""}],"conditionList":[{"status":{"abilityName":" Time","statusValue":"22:00"}},{"status":{"abilityName":"Location","statusValue":"Haidian District, Beijing"}},{"status":{"abilityName":"Location type","statusValue":"Home"}},{"status":{"abilityName":"wifi","statusValue":"Connected"}},{"status":{"abilityName":"Is it a working day","statusValue":"Yes"}},{"status":{"abilityName":"Bluetooth","statusValue":"Not connected"}},{"status":{"abilityName":"Weather","statusValue":"Cloudy at night"}},{"status":{"abilityName":"Motion status","statusValue":"Stationary"}},{"status":{"abilityName":"Device battery","statusValue":"87%"}}]}

[0074] The response information returned by the large model combined with the user operation log can be:

[0075] {"actionList":[{"action":{"appName":"iQiyi","statusValue":"Continue playing"}},{"action":{"appName":"Bilibili","statusValue":"Follow the show"}},{"action":{"appName":"Xiaohongshu","statusValue":"Hot outfits"}}]}

[0076] In this example, the user unlocked the phone, and the terminal device provided the operation information as well as scene information such as time, location (location type), WIFI and Bluetooth connection status, weather, exercise status and device power to the big model. The big model predicted that the user might need to use the "Continue Playing" function provided by the "iQiyi" application, the "Catch Up" function provided by the "Bilibili" application, and the "Popular Outfits" function provided by the "Little Red Book" application.

[0077] By adopting the method of this embodiment, the large model can more accurately predict the user's functional usage intention based on the current scenario information in the query information when using the user operation log as the response background knowledge, so that the terminal device can display the functional service plug-in composed of the corresponding plug-in functions on the user desktop in different scenarios, simplifying the user's function usage steps and improving the user experience.

[0078] Step S230 , based on the response information, an atomic component corresponding to the plug-in function is selected from the functional component library of each application program, and a plug-in matching the current scenario is generated using the atomic component.

[0079] Among them, the functional component library of each application may include functional components that are open to the system by system applications or third-party applications and can be used as desktop plug-in functions, and atomic components refer to the smallest, indivisible functional units, including but not limited to functions (Function), methods (Method), variables (Variable), constants (Constant), objects (Object), events (Event), messages (Message), services (Service), interfaces (Interface), etc. These atomic components can be combined and nested to construct specific application functions.

[0080] As mentioned above, the plug-in functions provided by third-party applications are developed and designed by the developers of the third-party applications. Therefore, the plug-in functions provided by the third-party applications to the plug-in management service have a fixed plug-in framework, that is, only one or more plug-in functions of a single third-party application can be displayed in a plug-in, which is inconvenient to use and it is difficult to ensure the compatibility of the plug-in framework with the user's desktop. For example, in existing devices such as mobile phones, when users manually add plug-in functions, they cannot add and display plug-ins whose plug-in framework is larger than the blank area of ​​the desktop.

[0081] Therefore, in an embodiment of the present application, after obtaining the large model to return the user's functional usage intention, it is not necessary to directly use the original plug-in provided by the third-party application. Instead, the atomic components corresponding to each function in the response information are obtained, and the system itself uses these atomic components to form a new plug-in that is different from the original fixed plug-in and is compatible with the user's desktop and system.

[0082] Specifically, step S230 may include: determining a corresponding plug-in template based on the number of plug-in functions matching the current scenario in the response information, the type of each plug-in function, and the current display interface of the terminal device.

[0083] In an embodiment of the present application, the operating system of the terminal device may provide a plug-in template (plug-in framework), and according to the number of plug-in functions contained in the response information of the large model, the type of plug-in functions, and the blank area in the current display interface (user desktop), a corresponding plug-in template may be selected from the pre-configured plug-in templates in the system.

[0084] Furthermore, in step S230, a plug-in matching the current scene is generated using atomic components, including: generating a plug-in visual image based on a plug-in template, wherein the plug-in template includes the size of the plug-in, the text format, and the layout of the interactive components in the plug-in; determining a plug-in display area that matches the plug-in visual image in the current display interface of the terminal device; adding the plug-in visual image to the plug-in display area, and establishing a mapping relationship between the area where each interactive component is located in the plug-in display area and the atomic components corresponding to the plug-in function, so that when a touch event occurs in the area where each interactive component is located, the corresponding plug-in function is called, thereby generating a plug-in matching the current scene.

[0085] Exemplarily, the plug-in generation method in the present application can be run by an additional system application in the system. After determining the plug-in framework, it can combine and layout the interactive components (such as buttons, text boxes, etc.) corresponding to multiple plug-in functions from different applications (including third-party applications) in a single plug-in and select the corresponding background image to generate a plug-in visual image.

[0086] After adding the plug-in visual image to the plug-in display area, establishing the mapping relationship between each interactive component and the corresponding atomic component can also be understood as processing touch events by setting PendingIntent in RemoteViews. Specifically, RemoteViews is a class that allows the creation and update of the plug-in's view hierarchy. PendingIntent is an object that describes the operation to be performed in the future. It allows predefined operations to be performed when a certain condition is met (such as the user touches an interactive component) without the main application running. Since the plug-in functions run in different processes of the application to which they belong, their views cannot be directly operated. We can define different view hierarchies for different interactive components in the same plug-in framework, use atomic components to define the actions that different interactive components need to perform when a touch event occurs, and bind the defined different PendingIntents to the views where different interactive components are located. In this way, plug-ins are created to provide shortcut functions or real-time information on the user's desktop, etc., and the layout and behavior of the plug-in are managed to manage the update and interaction of the plug-in.

[0087] Specifically, if you do not need to jump to the plug-in function of the main application, you can use the Intent mechanism to transfer data and trigger operations between the application and the corresponding plug-in. The plug-in can send broadcast Intents, and the main application can receive these Intents and perform corresponding operations, thereby triggering the update content in the plug-in according to the execution situation in the main application. If you need to jump to the plug-in function of the main application, you can set it to open and jump to the corresponding function interface of the main application when a touch event occurs in the interactive component for user use.

[0088] Figure 3 It is a schematic diagram comparing the display effects of a conventional plug-in according to an embodiment of the present application and a plug-in generated by the plug-in generation method according to an embodiment of the present application.

[0089] like Figure 3 As shown, the user desktop on the left uses the application itself to provide a plug-in framework, function A and function B belong to the same application, and both can display their interactive components in the same plug-in (plug-in 1), while function C and function D belong to another application, and both cannot be displayed in plug-in 1, but can only be displayed in plug-in 2, and both plug-in 1 and plug-in 2 are provided with fixed frames by the application, and their sizes are difficult to change. When function A, function B, function C and function D are displayed at the same time, the area on the user desktop that can display other content such as application icons will be limited, or when there are many original application icons on the user desktop, it is impossible to display all four functions on the user desktop as plug-in functions.

[0090] The right side is a plug-in generated by the plug-in generation method of the embodiment of the present application. Since the plug-in framework provided by the system is used, the system can rearrange and adjust the interactive components of each function in the framework, so that function A, function B, function C and function D are displayed in the same plug-in, occupying a relatively small display area on the user's desktop, which is more adaptable to the system and model, and also improves the user experience.

[0091] It should be emphasized that the plug-in generated by the plug-in generation method of the embodiment of the present application can not only be displayed on the user's desktop, but can also be configured to be displayed on the lock screen interface or the system floating window according to actual display requirements. The present application is not limited to this.

[0092] The above describes the specific settings and implementation methods of the embodiments of the present application from different perspectives. Using the method provided in the above embodiments, the predictive ability of the large model can be used to provide plug-in functions that are more in line with the personalized needs of users in the current scenario, simplify the user's function usage steps, and enhance the user experience. In addition, the present application can use the plug-in framework provided by the system to combine and display the plug-in functions provided by different applications, and overcome the display problems caused by the poor compatibility of the plug-in framework provided by the application itself with the system and model.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0094] As the implementation of the above methods, Figure 4 As shown, the embodiment of the present application also provides a plug-in generation device, which can be applied to a terminal device, and the device may include:

[0095] The query module 410 is used to generate query information based on at least current scene information in response to detecting information that meets the plug-in generation condition; wherein the information that meets the plug-in generation condition includes preset scene information and / or preset operation information, and the current scene information includes at least one of time, location type, weather, network connection status, device power, and user motion status;

[0096] The response acquisition module 420 is used to send the query information to the pre-trained big model, and obtain the response information corresponding to the query information returned by the big model using the user operation log as the response background knowledge; wherein the user operation log records the user's historical use records of the functions provided by each application in the terminal device, each use record contains the used function information and the use scenario information, and the response information includes at least one plug-in function generated by the big model that matches the current scenario;

[0097] The generation module 430 is used to select atomic components corresponding to the plug-in functions in the functional component library of each application based on the response information, and use the atomic components to generate a plug-in matching the current scenario.

[0098] Exemplarily, the query module 410 is used to: in response to detecting that the information meeting the plug-in generation condition includes preset scene information, obtain other scene information required to generate the query information; and use the preset scene information and other scene information as the current scene information.

[0099] Exemplarily, the preset operation information includes operation information of preset functions in the terminal device; the query module 410 is used to: in response to detecting that the information meeting the plug-in generation conditions includes the preset operation information, generate query information based on the current scene information and the preset operation information.

[0100] Exemplarily, the preset operation information includes plug-in function description information input by the user; the query module 410 is used to: in response to detecting that the information meeting the plug-in generation conditions includes the preset operation information, extract the plug-in function description information input by the user; and generate query information based on the current scene information and the plug-in function description information.

[0101] Exemplarily, the large model accesses the user operation log based on the function call interface; the response acquisition module 420 is used to:

[0102] The query information and the user ID are sent to the pre-trained large model, and the response information corresponding to the query information returned by the large model using the user operation log corresponding to the user ID as the response background knowledge is obtained.

[0103] The generation module 430 is used to generate a plug-in visual image based on a plug-in template, wherein the plug-in template includes the size of the plug-in, the text format, and the layout of the interactive components in the plug-in; determine a plug-in display area that matches the plug-in visual image in the current display interface of the terminal device; add the plug-in visual image to the plug-in display area, and establish a mapping relationship between the area where each interactive component is located in the plug-in display area and the atomic components corresponding to the plug-in function, so that when a touch event occurs in the area where each interactive component is located, the corresponding plug-in function is called, thereby generating a plug-in that matches the current scene.

[0104] The generation module 430 is further used to determine a corresponding plug-in template based on the number of plug-in functions matching the current scenario in the response information, the type of each plug-in function, and the current display interface of the terminal device.

[0105] The functions of each unit, module or sub-module in each device in the embodiments of the present application can refer to the corresponding description in the above method embodiments, and have corresponding beneficial effects, which will not be repeated here.

[0106] According to an embodiment of the present application, the present application also provides an electronic device, a computer-readable storage medium and a computer program product.

[0107] Figure 5 is a block diagram of an electronic device used to implement an embodiment of the present application. Figure 5 As shown, the electronic device includes: a memory 501 and a processor 502. The memory 501 stores a computer program that can be run on the processor 502. When the processor 502 executes the computer program, the method in the above embodiment is implemented. The number of the memory 501 and the processor 502 can be one or more.

[0108] The electronic device also includes:

[0109] The communication interface 503 is used to communicate with external devices and perform data exchange transmission.

[0110] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the memory 501, the processor 502 and the communication interface 503 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0111] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0112] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0113] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the present application.

[0114] It should be understood that the processor may be a CPU, or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), FPGAs or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the Advanced RISC Machines (ARM) architecture.

[0115] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0118] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0119] Any process or method described in the flow chart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0120] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or used in combination with these instruction execution systems, devices or apparatuses.

[0121] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0122] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0123] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope recorded in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A plug-in generation method, applied to a terminal device, comprising: In response to detecting information that meets the plug-in generation conditions, generating query information based on at least current scene information; wherein the information that meets the plug-in generation conditions includes preset scene information and / or preset operation information, and the current scene information includes at least one of time, location type, weather, network connection status, device power, and user motion status; The query information is sent to a pre-trained large model, and the response information corresponding to the query information is returned by the large model using the user operation log as the response background knowledge; wherein the user operation log records the user's historical use of the functions provided by each application in the terminal device, each use record contains the used function information and the use scenario information, and the response information includes at least one plug-in function generated by the large model that matches the current scenario; Based on the response information, an atomic component corresponding to the plug-in function is selected from the functional component library of each application program, and a plug-in matching the current scenario is generated using the atomic component.

2. The method according to claim 1, wherein: After responding to detecting information that meets the plug-in generation condition, the method further includes: In response to detecting that the information meeting the plug-in generation condition includes preset scenario information, acquiring other scenario information required to generate the query information; The preset scene information and the other scene information are used as current scene information.

3. The method according to claim 1, wherein: The preset operation information includes operation information of preset functions in the terminal device; The step of generating query information based on at least current scene information in response to detecting information that meets the plug-in generation condition includes: In response to detecting that the information meeting the plug-in generation condition includes preset operation information, query information is generated based on the current scene information and the preset operation information.

4. The method according to claim 1, wherein: The preset operation information includes the plug-in function description information input by the user; The step of generating query information based on at least current scene information in response to detecting information that meets the plug-in generation condition includes: In response to detecting that the information meeting the plug-in generation condition includes preset operation information, extracting the plug-in function description information input by the user; Generate query information based on the current scene information and the plug-in function description information.

5. The method according to claim 1, wherein: The large model accesses the user operation log based on the function call interface; the query information is sent to the pre-trained large model, and the response information corresponding to the query information returned by the large model using the user operation log as the response background knowledge includes: The query information and the user identification are sent to a pre-trained large model, and response information corresponding to the query information returned by the large model using the user operation log corresponding to the user identification as response background knowledge is obtained.

6. The method according to claim 1, wherein: The step of using the atomic component to generate a plug-in matching the current scene includes: Generating a plug-in visual diagram based on a plug-in template, wherein the plug-in template includes the size of the plug-in, text format, and layout of interactive components in the plug-in; Determine, on the current display interface of the terminal device, a plug-in display area that matches the plug-in visual image; The plug-in visual image is added to the plug-in display area, and a mapping relationship is established between the area where each interactive component is located in the plug-in display area and the atomic components corresponding to the plug-in function, so that when a touch event occurs in the area where each interactive component is located, the corresponding plug-in function is called, thereby generating a plug-in that matches the current scene.

7. The method according to claim 6, wherein: Before generating the plugin visual map based on the plugin template, it also includes: Based on the number of plug-in functions matching the current scenario in the response information, the type of each plug-in function, and the current display interface of the terminal device, a corresponding plug-in template is determined.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

9. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program / instructions, which, when executed by a processor, implement the steps of the method according to claims 1-7.

Images