# US 11,443,188 B2 · Application generation based on neural network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,188 B2 - Document ID: US11443188B2 - Status: Granted - Kind: B2 - Application number: 16/798,611 - Filed: 2020-02-24 - Published: 2021-08-26 - Granted: 2022-09-13 - Earliest claimed: 2020-02-24 - Assignees: Sony Group Corporation - Applicants: Sony Group Corporation - Inventors: Jenke Wu Kuo - Web page: https://patentgrep.com/patent/US11443188B2 ## CPC - G06N 3/08: Learning methods - G06F 8/30: Creation or generation of source code - G06F 8/76: Adapting program code to run in a different environment; Porting - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0475: Generative networks - G06N 3/09: Supervised learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A server that includes circuitry and memory is provided. The memory stores a trained neural network model to provide a first application associated with a first service. The first application is executable on a first electronic device associated with first capability information. The circuitry receives, from a second electronic device, second capability information associated with the second electronic device. The circuitry further generates a second program code based on the received second capability information of the second electronic device and a first program code associated with first application. The circuitry further generates a second application associated with the first service based on the generated second program code. The circuitry further transmits the generated second application to the second electronic device. The generated second application may be executed on the second electronic device to provide the first service on the second electronic device. ## Claims ### Claim 1 A server, comprising: a memory configured to store a trained neural network model to provide a first application associated with a first service, wherein the first application is executable on a first electronic device associated with first capability information; and circuitry coupled with the memory, the circuitry is configured to: receive, from a second electronic device different from the first electronic device, second capability information associated with the second electronic device; generate a second program code based on the received second capability information of the second electronic device and a first program code associated with the first application; generate a second application associated with the first service based on the generated second program code; and transmit the generated second application to the second electronic device, wherein the generated second application is executed on the second electronic device to provide the first service on the second electronic device. ### Claim 2 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to re-train the neural network model based on the second capability information and the generated second application for the second electronic device. ### Claim 3 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to perform at least one of a code inspection, a unit test, an integration test, or a system test to generate the second application based on the generated second program code. ### Claim 4 (depends on 1) The server according to claim 1, wherein the first capability information associated with the first electronic device and the second capability information associated with the second electronic device includes information about at least one of hardware capability or software capability. ### Claim 5 (depends on 4) The server according to claim 4, wherein the hardware capability includes at least one of an image content rendering capability, an audio content rendering capability, a closed caption capability, a size of a display screen, a resolution of the display screen, a processor speed, a size of storage device, a hardware architecture, a type of input device, a network capability, a type of in-built sensor, a battery capacity, or a power of audio device. ### Claim 6 (depends on 4) The server according to claim 4, wherein the software capability includes at least one of a type and a version of operating system (OS), a programming language, security settings, a version of web browser, a communication protocol, or a current application version related to the first service. ### Claim 7 (depends on 1) The server accordingly to claim 1, wherein the circuitry is further configured to update the first program code of the first application based on the second capability information to generate the second application for the second electronic device. ### Claim 8 (depends on 7) The server accordingly to claim 7, wherein the circuitry is further configured to update a first programming language of the first program code of the first application based on a second programming language indicated by the second capability information, to generate the second application for the second electronic device, wherein the second electronic device supports the second programming language. ### Claim 9 (depends on 1) The server accordingly to claim 1, wherein a number of first features in the first application associated with the first service is higher or lower than a number of second features in the generated second application, based on the first capability information of the first electronic device and the second capability information of the second electronic device. ### Claim 10 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to: receive, from the second electronic device, a first user-input indicative of a media content type associated with the first service; generate the second program code based on the received first user-input and the received second capability information; and generate the second application associated with the first service based on the generated second program code. ### Claim 11 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to: determine a set of configuration values for at least one setting of the second electronic device based on the second capability information; and transmit, to the second electronic device, the determined set of configuration values for the execution of the second application. ### Claim 12 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to transmit, to the second electronic device, a user-interface (UI) element associated with the second application, and wherein the UI element is configured to install or update the second application on the second electronic device. ### Claim 13 (depends on 1) The server according to claim 1, wherein the circuitry is further configured to: receive a second user-input from the second electronic device to update the second application; generate a third program code based on the generated second program code, the received second user-input, and the second capability information; update the second application based on the generated third program code; and transmit the updated second application to the second electronic device, wherein the updated second application is executed on the second electronic device to provide the first service. ### Claim 14 (depends on 13) The server according to claim 13, wherein the circuitry is further configured to re-train the neural network model based on the second user-input, the second capability information and the updated second application for the second electronic device. ### Claim 15 A method, comprising: in a server: storing a trained neural network model to provide a first application associated with a first service, wherein the first application is executable on a first electronic device associated with a first capability information; receiving, from a second electronic device different from the first electronic device, second capability information associated with the second electronic device; generating a second program code based on the received second capability information of the second electronic device and a first program code associated with the first application; generating a second application associated with the first service based on the generated second program code; and transmitting the generated second application to the second electronic device, wherein the generated second application is executed on the second electronic device to provide the first service on the second electronic device. ### Claim 16 (depends on 15) The method according to claim 15, further comprising re-training the neural network model based on the second capability information and the generated second application for the second electronic device. ### Claim 17 (depends on 15) The method according to claim 15, wherein the first capability information associated with the first electronic device and the second capability information associated with the second electronic device includes information about at least one of hardware capability or software capability. ### Claim 18 (depends on 15) The method according to claim 15, further comprising updating the first program code of the first application based on the second capability information, to generate the second application for the second electronic device. ### Claim 19 (depends on 15) The method according to claim 15, wherein a number of first features in the first application associated with the first service is higher or lower than a number of second features in the generated second application, based on the first capability information of the first electronic device and the second capability information of the second electronic device. ### Claim 20 A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by a server, causes the server to execute operations, the operations comprising: storing a trained neural network model to provide a first application associated with a first service, wherein the first application is executable on a first electronic device associated with first capability information; receiving, from a second electronic device different from the first electronic device, second capability information associated with the second electronic device; generating a second program code based on the received second capability information of the second electronic device and a first program code associated with the first application; generating a second application associated with the first service based on the generated second program code; and transmitting the generated second application to the second electronic device, wherein the generated second application is executed on the second electronic device to provide the first service on the second electronic device.