system

Abstract

We provide the system. [Solution] A means for collecting past installation increase data, A method for predicting future increases in the number of installations using machine learning algorithms, A means for creating a list of equipment to be installed based on the predicted increase, A means of obtaining data center resource information, A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center, A system that includes this.

Description

Technical Field

[0005]

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. <00000l0>

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern data centers, while the installation of equipment is increasing, it is becoming difficult to optimize the resource management (power supply, air conditioning, space). Therefore, if resources are not allocated appropriately, the efficiency of the data center may decrease and the operating cost may increase. In addition, manual resource allocation requires time and labor, and there is a problem of a high risk of human error.

Means for Solving the Problems

[0005] This invention solves the above problem by providing a system that collects past installation increase data and uses a machine learning algorithm to predict future installation increases based on that data. Furthermore, it creates a list of equipment to be installed based on the predicted increase and obtains data center resource information. The system also includes means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center. This system enables optimal resource management and efficient operation.

[0006] "Past installation increase data" refers to records of equipment installations and increases in data centers over the past few years.

[0007] A "machine learning algorithm" is an algorithm that learns past data patterns to predict and classify future data.

[0008] "Future installation increase" refers to the number of devices that will be installed in data centers in the future, as predicted using machine learning algorithms.

[0009] The "List of Equipment to be Installed" refers to a list of equipment that is planned to be installed in the data center next year, based on the projected increase in installations.

[0010] "Data center resource information" refers to information about the resources that a data center possesses, such as power, air conditioning, and available space.

[0011] "Equipment requirements" refer to the resources that a particular piece of equipment needs (e.g., power capacity, cooling capacity, installation space).

[0012] "Comparison" refers to the act of comparing the requirements of the equipment to be installed with the resource information of the data center to evaluate and determine the degree of compatibility.

[0013] "Allocating equipment to the appropriate data center" refers to selecting a data center that maximizes resource utilization efficiency and can accommodate the equipment without excess or deficiency, and then placing the equipment in that data center. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that compares equipment to be installed in a data center with the resources available in the data center, and efficiently allocates the equipment. A specific embodiment of this system is described below.

[0036] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0037] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0038] Next, the server uses the acquired data to train a machine learning algorithm (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0039] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0040] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0041] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0042] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0043] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user logs into the system. The user enters appropriate authentication information (such as username and password) and is granted access to the system.

[0047] Step 2:

[0048] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query against the database to retrieve installation records for the past three years.

[0049] Step 3:

[0050] The server uses the acquired installation data to train a machine learning model. For example, a linear regression model can be used to learn past installation trends.

[0051] Step 4:

[0052] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0053] Step 5:

[0054] The server generates a list of equipment to be installed in the next fiscal year based on predictions. This list includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0055] Step 6:

[0056] The server retrieves resource information from the data center. It issues queries to the facility management system to obtain information such as power capacity, cooling capacity, and available space for each data center.

[0057] Step 7:

[0058] Compare the requirements of the equipment where the servers are planned to be installed with the resources of the data center. Evaluate whether the requirements of each piece of equipment can be met with the current resources of the data center.

[0059] Step 8:

[0060] The server allocates equipment to each data center. Considering resource utilization efficiency, an allocation plan is developed to place equipment in the most suitable data center.

[0061] Step 9:

[0062] The server saves the allocation results to the database. The allocation plan is saved so that it can be referenced and modified later.

[0063] Step 10:

[0064] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] As the amount of equipment planned for installation in data centers increases, efficiently managing resources and appropriately allocating equipment without excess or shortage becomes challenging. In particular, there is a need for a means to accurately understand future expansion forecasts and data center resource information, and to make optimal allocations. Furthermore, it is crucial that the system is easily accessible to users and that the status can be checked from a management screen.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for a user to enter authentication information and log in to the system; means for collecting past installation increase data; means for predicting future installation increases using a machine learning algorithm; means for creating a list of equipment to be installed based on the predicted increase; means for obtaining data center resource information; means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center; and means for saving the allocation results to a database and notifying the user of that information. This makes it possible to maximize resource utilization efficiency and realize a system that is highly convenient for users.

[0070] A "user" refers to an individual or organization that accesses and operates a system.

[0071] "Authentication information" refers to information used to identify a user and verify their access rights to the system, such as a user ID and password.

[0072] "Logging in" refers to the process of accessing and making available a system using authentication credentials.

[0073] A "server" refers to a computer system that performs tasks such as data processing and resource management.

[0074] "Installation increase data" refers to records of equipment newly installed in data centers in the past.

[0075] A "machine learning algorithm" refers to a statistical method used to analyze data and make predictions about future trends.

[0076] The "list of equipment to be installed" refers to a list of equipment that is scheduled to be installed in the future.

[0077] A "data center" refers to a facility where computers and other related equipment are installed.

[0078] "Resource information" refers to management information such as power capacity, cooling capacity, and available space within a data center.

[0079] "Equipment requirements" refer to the specific conditions such as power, cooling, and space required by the equipment to be installed.

[0080] "Comparison" refers to the process of matching the requirements of the equipment to be installed with the resource information of the data center and evaluating their suitability.

[0081] "Allocation" refers to the process of deciding where to place the equipment to be installed in the most appropriate data center.

[0082] A "database" refers to an information system that systematically manages large amounts of data and facilitates searching and updating.

[0083] "Notification" refers to the act of a system communicating information to a user.

[0084] A "facility management system" refers to a software system used to manage the status of resources and equipment within a data center.

[0085] A "resource allocation plan" refers to a detailed plan for efficiently using resources within a data center and arranging equipment accordingly.

[0086] This invention relates to a system for efficiently allocating equipment to be installed in a data center. This system enables users to optimize resource management with simple operations and formulate an appropriate equipment placement plan based on predictions.

[0087] First, the user logs into the system. The user enters appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen. The authentication process uses the user ID and password, which the server verifies against the database.

[0088] Next, the server collects past installation increase data. Specifically, the server issues queries to the database to extract past installation records. An example query is "SELECT FROM InstallationRecords WHERE Year >= 2019;". This data is temporarily stored in the server's memory.

[0089] After collecting historical data, the server uses a machine learning algorithm to predict future increases in the number of installations. The server builds and trains a linear regression model using machine learning libraries such as scikit-learn. The server uses the trained model to make predictions and generates a list of planned installations for the next year based on the results.

[0090] Next, the server retrieves resource information from the data center. The server issues a query to the facility management system to obtain the latest resource status. An example query is "SELECT FROM ResourceStatus;". This resource information is also temporarily stored in the server's memory.

[0091] The server matches the requirements of the equipment to be installed with the data center's resource information. It extracts the requirements for each piece of equipment (e.g., power, cooling, space) and compares them with the retrieved resource information. This verifies that resources are adequately met and helps develop an efficient resource allocation plan.

[0092] As a concrete example, based on records showing an increase of 20, 25, and 30 servers over the past three years, we predict that 35 servers will be needed in the next fiscal year. Subsequently, we obtain resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, available space 50 racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, available space 40 racks). If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, we decide to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0093] Finally, the server saves the allocation results to the database. The server then notifies the user of this information, and the user can check the allocation results through the system's administration screen. This enables optimal resource management and efficient operation.

[0094] An example of a prompt message is: "Train a linear regression model using installation data from the past three years to predict next year's server installation plan. Also, obtain the latest resource information for the data center and develop a deployment plan to optimally allocate equipment."

[0095] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0096] Step 1:

[0097] The user logs into the system.

[0098] The user accesses the system and enters authentication information (e.g., user ID and password). The server verifies this entered authentication information against the database. If authentication is successful, the server starts a session for the user and grants access to the administration screen. The input is the user ID and password, and the output is the authentication session.

[0099] Step 2:

[0100] The server collects past installation increase data.

[0101] The server issues an SQL query to the database to extract past installation records. Specifically, it executes the query "SELECT FROM InstallationRecords WHERE Year >= 2019;". The server temporarily stores the retrieved data in memory. The input is a query for installation increase data, and the output is past installation record data.

[0102] Step 3:

[0103] The server uses a machine learning algorithm to predict future increases in installation numbers.

[0104] The server loads machine learning libraries such as scikit-learn and builds a linear regression model using historical installation data. Next, it trains the model to predict future installation increases. The input is historical installation records, and the output is the predicted installation increase for the next year.

[0105] Step 4:

[0106] The server creates a list of equipment scheduled for installation in the next fiscal year.

[0107] The server creates a list of planned equipment installations for the next fiscal year based on the predicted increase in installations. This generates a list of specific equipment to be installed. The input is the predicted increase in installations, and the output is the list of planned equipment installations for the next fiscal year.

[0108] Step 5:

[0109] The server retrieves resource information from the data center.

[0110] The server issues an SQL query to the equipment management system to retrieve the latest resource information. Specifically, it executes the query "SELECT FROM ResourceStatus;". The server temporarily stores this information in memory. The input is the query for resource information, and the output is the latest resource information data.

[0111] Step 6:

[0112] Compare the requirements of the equipment where the server will be installed with the resources of the data center.

[0113] The server loads a list of planned equipment and resource information, and compares the requirements (e.g., power, cooling, space) and resources for each. This verifies that the resources are adequately met. The input is the list of planned equipment and resource information, and the output is a resource allocation plan.

[0114] Step 7:

[0115] The server allocates the equipment to the appropriate data center.

[0116] Based on the comparison results, the server allocates the equipment to be installed in each data center. This ensures optimal resource utilization. The server saves the allocation results to a database and formulates a deployment plan. The input is the resource allocation plan, and the output is the allocation results and the deployment plan.

[0117] Step 8:

[0118] The server notifies the user of the allocation result.

[0119] The server notifies the user of the allocation results, making them available for viewing from the system's administration screen. This allows users to achieve optimal resource management. The input is the allocation results, and the output is the notification to the user.

[0120] (Application Example 1)

[0121] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0122] There is a need to simultaneously address two different challenges: efficiently managing data center resources and optimizing parking locations for autonomous vehicles. This requires streamlining complex tasks such as data center equipment installation planning, vehicle resource management, and parking location selection, thereby reducing costs and improving operational efficiency.

[0123] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0124] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for collecting vehicle sensor data and evaluating parking spaces, and means for comparing vehicle resources with the conditions of the parking space and selecting the optimal parking location. This enables efficient management of data center resources and optimization of parking location selection for autonomous vehicles.

[0125] "Installation increase data" refers to data on the historical increase in the number of equipment installations in data centers and other related facilities.

[0126] A "machine learning algorithm" is a mathematical method that learns patterns from past data to make predictions and decisions about the future.

[0127] The "List of Equipment to be Installed" is a list of equipment that is planned to be installed in the data center in the future, based on the predicted increase in installations.

[0128] "Data center resource information" refers to information about the current state of resources available to the data center, such as power capacity, cooling capacity, and available space.

[0129] "Equipment requirements" refer to the conditions such as power, cooling, and space necessary for the equipment to be installed to operate normally.

[0130] "Sensor data" refers to information such as battery level, internal temperature, and available space collected by sensors installed in autonomous vehicles.

[0131] "Parking space evaluation" is the process of using the vehicle's cameras and sensors to determine how available or appropriate a parking space is at present.

[0132] An "optimal parking spot" is the most suitable parking location for a vehicle, based on its resource information and the conditions of the parking space.

[0133] This invention provides a system that integrates data center resource management and the optimization of parking locations for autonomous vehicles. This system includes the following means:

[0134] First, the server collects historical installation growth data. This data is obtained from installation records stored in a database for the past several years. The server queries the database to extract historical installation records.

[0135] Next, the server uses the acquired data to train a machine learning algorithm. For example, it uses a linear regression model to predict future increases in the number of installations. Based on the prediction results, it generates a list of equipment scheduled for installation in the following year.

[0136] The server also retrieves resource information from the data center. This resource information is obtained from the data center's facility management system. Queries are issued to the facility management system to retrieve the latest resource status.

[0137] Next, the server compares the requirements of the equipment to be installed (e.g., power consumption, cooling requirements, installation space) with the resources of the data center to ensure that the resources are adequately met. Then, it allocates the equipment to the appropriate data center.

[0138] Furthermore, the server collects data from the vehicle's sensors, including battery level, internal temperature, and available space. It also uses data from the vehicle's cameras and sensors to assess the availability of parking spaces.

[0139] The server uses the collected data to compare the vehicle's resources with the conditions of the parking space and select the optimal parking location. A linear regression model is applied to this process to predict the most suitable parking location for the vehicle.

[0140] The hardware used includes cameras, temperature sensors, space sensors, and servers mounted on the autonomous vehicle. The software used includes OpenCV for data processing, NumPy for data analysis, and scikit-learn for machine learning models.

[0141] As a concrete example, real-time data is collected from in-vehicle cameras and sensors, and this data is processed using OpenCV. For instance, to evaluate the availability of parking spaces, camera data is binarized and the number of white pixels is counted. Based on sensor data (battery level, internal temperature, available space), basic conditions are evaluated, and the optimal parking location is selected using a linear regression model.

[0142] An example of a prompt message is: "Analyze the availability of parking spaces and recommend the best parking spot considering the vehicle's battery level, interior temperature, and available space."

[0143] This will enable more efficient resource management in data centers and optimize the selection of parking locations for autonomous vehicles.

[0144] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0145] Step 1:

[0146] The server collects historical installation data from the database. First, it issues a query to the database to extract past installation records. This data includes the quantity of equipment installed over the past few years, the installation date and time, and the installation location. Using the configured query as input, the server obtains historical installation data as output.

[0147] Step 2:

[0148] The server trains a machine learning algorithm using collected installation increase data. It applies a linear regression model to learn trends for predicting future installation increases. Historical installation data is used as input, and the optimal regression model is output through computation.

[0149] Step 3:

[0150] The server creates a list of equipment to be installed based on the predicted increase in capacity. Based on the prediction results, it generates a list of equipment expected to be installed in the next fiscal year. Machine learning prediction results are used as input, and a list of equipment to be installed is generated as output.

[0151] Step 4:

[0152] The server retrieves data center resource information. This is done by querying the facility management system to obtain the latest information on power capacity, cooling capacity, and available space. A query is set as the input, and data center resource information is obtained as the output.

[0153] Step 5:

[0154] The server compares the requirements of the equipment to be installed (power consumption, cooling requirements, installation space) with the resource information of the data center. It checks whether each piece of equipment meets the requirements and allocates the equipment to the appropriate data center. The equipment requirements and data center resource information are used as input, and the output is the allocation result of the optimal installation location.

[0155] Step 6:

[0156] The server collects sensor data (battery level, internal temperature, available space) from the autonomous vehicle. It acquires real-time data from each sensor and takes the sensor data as input. Status information for each sensor is obtained as output.

[0157] Step 7:

[0158] The server evaluates the availability of parking spaces based on data from the vehicle's cameras and sensors. It uses OpenCV to process camera data and evaluate available spaces. Camera data is used as input, and the evaluation result for available spaces is obtained as output.

[0159] Step 8:

[0160] The server compares vehicle resources and parking space conditions based on collected data to select the optimal parking location. A linear regression model is used to calculate a parking location evaluation score. Sensor data and the evaluation results of available spaces are used as input, and the output is the selection result of the optimal parking location.

[0161] Step 9:

[0162] The server saves the allocation results and parking location selection results to a database and notifies the user of this information. It records the allocation results and optimal parking location information in the database and notifies the user. Allocation results and selection results are used as input, and user notifications are generated as output.

[0163] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0164] This invention combines a system that compares the equipment to be installed in a data center with the resources available in the data center to efficiently allocate the equipment, with an emotion engine that recognizes user emotions. A specific embodiment of this system is described below.

[0165] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0166] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0167] Next, the server uses the acquired data to train a machine learning model (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0168] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0169] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0170] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0171] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's voice, facial expressions, and input content to identify the user's emotional state. The server analyzes the emotional data obtained from the emotion engine and adjusts the system's display interface and operation flow based on the results. For example, if the user is stressed, the system will either provide a simpler interface or enhance its assistance functions.

[0172] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0173] Next, the emotion engine recognizes the user's emotional state. For example, if it detects that the user is feeling stressed during an interaction, the server simplifies the interface and adjusts it to allow the user to interact more smoothly. Furthermore, if the emotion engine is satisfied, it provides detailed resource allocation options to allow the user to engage more deeply.

[0174] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation. The combination with the emotion engine improves the user experience and reduces stress and frustration.

[0175] The following describes the processing flow.

[0176] Step 1:

[0177] The user logs into the system. The user enters appropriate authentication information, such as a username and password, to obtain permission to access the system.

[0178] Step 2:

[0179] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query to extract data in order to retrieve installation records for the past three years.

[0180] Step 3:

[0181] The server uses the acquired installation data to train a machine learning model (e.g., a linear regression model). This allows the model to learn past data patterns and prepare to predict future increases in installation numbers.

[0182] Step 4:

[0183] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0184] Step 5:

[0185] The server generates a list of equipment to be installed in the next fiscal year based on predictions. Specifically, it creates a list that includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0186] Step 6:

[0187] The server retrieves data center resource information (e.g., power capacity, cooling capacity, available space). It then issues queries to the facility management system to obtain the latest resource status.

[0188] Step 7:

[0189] The system compares the requirements of the equipment where the servers are planned to be installed with the resources of the data center. It evaluates whether the requirements of each piece of equipment can be met with the current resources of the data center and determines the degree of suitability.

[0190] Step 8:

[0191] The server allocates equipment to each data center. It selects data centers that maximize resource utilization efficiency and can accommodate the necessary equipment without excess or shortage. It then develops an allocation plan and places the equipment in the corresponding data centers.

[0192] Step 9:

[0193] The server saves the allocation results to the database. The allocation plan is saved to the database so that it can be referenced and modified later.

[0194] Step 10:

[0195] The emotion engine recognizes the user's emotional state. It analyzes the voice, facial expressions, and input content the user provides during operation to identify stress levels and satisfaction levels.

[0196] Step 11:

[0197] The server adjusts the system's display interface and operation flow based on data obtained from the emotion engine. For example, if the system detects that the user is stressed, it simplifies the interface and enhances assistance features.

[0198] Step 12:

[0199] The server uses the sentiment engine's results to inform the user of the allocation decision in the most optimal way. For example, when the user is satisfied, it provides detailed resource allocation options, allowing the user to be more deeply involved.

[0200] Step 13:

[0201] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0202] In this way, the system utilizes an emotion engine to operate in accordance with the user's emotional state, achieving optimal resource management and efficient data center utilization.

[0203] (Example 2)

[0204] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0205] Ensuring consistency between the equipment planned for installation in the data center and the actual resources available, and efficiently allocating equipment, are crucial requirements. Furthermore, improving system usability and reducing user stress are also important challenges.

[0206] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0207] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for obtaining data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means including an emotion engine that recognizes user emotions, and means for analyzing emotion data obtained from the emotion engine and adjusting the system interface and operation flow. This enables efficient allocation of equipment, improved user operability, and reduced stress.

[0208] "Past installation increase data" refers to record data regarding equipment installed in data centers in the past and the increase in that number.

[0209] A "machine learning algorithm" is a computational method used to learn patterns and rules from data and perform predictions and classifications.

[0210] The "List of Equipment to be Installed" is information that shows a list of equipment that is planned to be installed in the data center in the next fiscal year.

[0211] "Data center resource information" refers to information about the resources necessary for installing equipment in a data center, such as power capacity, cooling capacity, and available space.

[0212] "Requirements for equipment to be installed" refers to the resource requirements, such as power, cooling, and space, that the equipment to be installed in the data center will need.

[0213] An "emotion engine" is a system that analyzes and identifies a user's emotional state based on their voice, facial expressions, input content, and other factors.

[0214] "Means for adjusting the interface and operation flow" refers to functions that change and optimize the system's display screen and operation procedures based on the user's emotional state.

[0215] "Allocation results" refer to information regarding the plan for efficiently placing equipment in each data center and the results thereof.

[0216] This invention provides a system that efficiently compares equipment to be installed in a data center with the resources of the data center and allocates the equipment optimally. Furthermore, it incorporates an emotion engine that recognizes user emotions to improve usability.

[0217] First, the user logs into the system. The user uses a browser or a dedicated application to enter appropriate authentication information (ID and password). The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the user can access the administration screen.

[0218] Next, the server collects historical installation increase data. This data is obtained from equipment installation records for the past several years stored in the database. An SQL query is executed to extract the data in a format such as "SELECT FROM installation_records WHERE year BETWEEN(registered trademark) 2019 AND 2021;".

[0219] Based on the acquired data, the server trains a linear regression model using a machine learning library (e.g., Scikit-learn). This model is used to predict future increases in the number of installations. For example, if past installation data shows 20, 25, and 30, it can predict 35 for the following year.

[0220] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year. This equipment list is saved in JSON or CSV format and used for future management.

[0221] Next, the server retrieves resource information for the data center. This resource information includes power capacity, cooling capacity, and available space. The server issues a query to the facility management system and retrieves the data in a format such as "SELECT FROM resource WHERE datacenterID = 1;".

[0222] Based on the acquired resource information, the server compares the requirements of the planned equipment (power, cooling, space) with the resources of the data center. For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server will evaluate the resources of each data center.

[0223] Based on the comparison results, the servers allocate equipment to each data center. The allocation results are formulated as a specific deployment plan, such as "20 servers in Data Center 1 and 15 servers in Data Center 2." This plan is stored in a database and used for future implementation.

[0224] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The server invokes the emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input. Based on the resulting emotion data, it adjusts the interface and operation flow.

[0225] For example, if the server detects that a user is experiencing stress while operating the system, it can simplify the interface and streamline the operation. Furthermore, if the user is satisfied, it can provide more detailed resource allocation options.

[0226] As a result, this system achieves efficient allocation of equipment, improved user experience, and reduced stress.

[0227] A concrete example would be a user logging into the system and seeing records showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the system predicts that 35 servers will be needed in the next fiscal year. Next, it obtains resource information for each data center and decides to allocate 20 servers to data center 1 and 15 servers to data center 2.

[0228] Furthermore, the emotion engine detects when the user is experiencing stress during their interaction, and the server provides a simple interface. In this way, the system's usability and the user experience are optimized.

[0229] An example of a prompt message for a generating AI model is, "Generate a list of servers to be installed in the next fiscal year and efficiently allocate them to each data center."

[0230] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0231] Step 1: User Login

[0232] Specific operation and input / output:

[0233] Users access the system using a browser or a dedicated application.

[0234] The user enters authentication information such as their ID and password.

[0235] Input: User authentication information (ID and password)

[0236] The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the server grants the user access to the administration screen.

[0237] Output: Authentication success / failure result and access rights to the administration screen

[0238] Step 2: Collecting past installation increase data

[0239] Specific operation and input / output:

[0240] The server executes SQL queries against the database to retrieve equipment installation records for the past several years.

[0241] Input: Installation records stored in the database

[0242] For example, execute a query like "SELECT FROM Installation Records WHERE Year BETWEEN 2019 AND 2021;".

[0243] Output: Past installation increase data

[0244] Step 3: Training and predicting machine learning models

[0245] Specific operation and input / output:

[0246] The server uses the collected data to train a linear regression model using a machine learning library (e.g., Scikit-learn).

[0247] Input: Past installation increase data

[0248] The server inputs new data into the trained model and predicts the increase in equipment installations for the following year.

[0249] Example: If past installation data shows 20, 25, and 30, then the forecast for the next year is 35.

[0250] Output: Predicted increase in the number of installations for the next fiscal year

[0251] Step 4: Generating the equipment list for the next fiscal year

[0252] Specific operation and input / output:

[0253] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year.

[0254] Input: Predicted increase in the number of installations for the next fiscal year

[0255] This device list is saved in JSON or CSV format.

[0256] Output: List of equipment scheduled for installation in the next fiscal year

[0257] Step 5: Obtain data center resource information

[0258] Specific operation and input / output:

[0259] The server issues a query to the data center's facility management system to retrieve resource information.

[0260] Input: Query to retrieve resource information

[0261] For example, execute the query "SELECT FROM resource WHERE datacenterID = 1;".

[0262] Output: Data center resource information (power capacity, cooling capacity, available space, etc.)

[0263] Step 6: Comparison of requirements and resources for the equipment to be installed.

[0264] Specific operation and input / output:

[0265] The server compares the requirements of each device with the resource information of the data center.

[0266] Input: Requirements for the equipment to be installed (power, cooling, space), data center resource information

[0267] For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the resource information is evaluated against those requirements.

[0268] Output: Resource evaluation results

[0269] Step 7: Develop equipment allocation and placement plans.

[0270] Specific operation and input / output:

[0271] Based on the comparison results, the servers efficiently allocate equipment to each data center.

[0272] Input: Resource evaluation results

[0273] The allocation plan is then specified, for example, "20 units in Data Center 1, and 15 units in Data Center 2."

[0274] The generated deployment plan is saved in the database.

[0275] Output: Layout plan

[0276] Step 8: User emotion recognition by the emotion engine

[0277] Specific operations and input / output:

[0278] The server calls an emotion engine (e.g., EmotionAPI) to analyze the user's voice, expression, and input content.

[0279] Input: User's voice, expression, input content

[0280] The server identifies the user's emotional state (e.g., stress, satisfaction) from the analysis results.

[0281] Output: Emotional data

[0282] Step 9: Interface adjustment

[0283] Specific operations and input / output:

[0284] The server adjusts the interface and operation flow based on the user's emotional data.

[0285] Input: Emotional data

[0286] For example, if the user is feeling stressed, a simplified interface is provided.

[0287] Output: Adjusted interface, operation flow

[0288] Step 10: Saving and notifying the results

[0289] Specific operations and input / output:

[0290] The server saves the final allocation result and the user's operation content to the database.

[0291] Input: Final allocation result, user's operation content

[0292] The server notifies the user's terminal that there is new information.

[0293] Output: Saved data, notification messages

[0294] (Application Example 2)

[0295] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0296] In data centers, expanding equipment and managing resources are crucial for efficient operation and optimal resource allocation. However, performing these tasks manually is complex and time-consuming, and can lead to operational errors and decreased efficiency, especially depending on the user's emotional state. Therefore, there is a need for a system that uses historical data for prediction, automated resource allocation, and adapts the user interface according to the user's emotional state.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0298] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for recognizing the user's emotions, and means for adjusting the system's operating interface based on the user's emotions. This enables efficient and appropriate equipment allocation and flexible interface adjustment according to the user's emotional state.

[0299] "Installation increase data" refers to records of increases or decreases in the number of devices and equipment installed in the past.

[0300] A "machine learning algorithm" refers to a mathematical method for learning patterns from data and making future predictions or classifications based on those patterns.

[0301] A "list of equipment scheduled for installation" is a list of equipment and facilities scheduled for installation in the future.

[0302] A "data center" is a facility where a large number of computers and storage devices are centrally installed for data storage and processing.

[0303] "Resource information" refers to information regarding the utilization status of resources such as the power capacity, cooling capacity, and free space of a data center.

[0304] "Equipment requirements" refer to the conditions and specifications such as power, cooling, and space required for equipment and facilities to operate.

[0305] "User emotions" refer to the psychological and physiological states or moods of users who operate the system.

[0306] An "operation interface" refers to the screens and input means for users to interact with and operate the system.

[0307] An "emotion recognition means" refers to technologies and devices for analyzing users' voices and expressions to identify their emotional states.

[0308] "Means for allocating equipment to an appropriate data center" refers to methods and algorithms for placing equipment in a data center that meets the requirements of the equipment scheduled for installation.

[0309] "Means for adjusting the operation interface of the system based on emotions" refers to methods and technologies for changing the operation screen and input method considering the emotional state of the user.

[0310] This invention is a system that improves the efficiency of equipment installation and user experience in data centers. The system collects historical installation growth data and uses machine learning algorithms to predict future installation growth. Based on the predicted growth, it creates a list of equipment to be installed and allocates equipment to appropriate data centers by comparing data center resource information with equipment requirements. Furthermore, it includes a function to recognize user emotions and adjust the operating interface based on those emotions.

[0311] 1. Hardware and software used

[0312] The system is implemented using the following hardware and software:

[0313] server:

[0314] Computational resources for data collection and machine learning.

[0315] Connect to the database and retrieve past installation increase data.

[0316] Perform calculations to formulate equipment allocation and placement plans.

[0317] camera:

[0318] A webcam that captures the user's facial image for emotion recognition.

[0319] DeepFace:

[0320] An emotion recognition library for analyzing user emotions.

[0321] scikit-learn:

[0322] A library for predicting future increases in installation numbers using machine learning algorithms (linear regression models).

[0323] Tkinter:

[0324] A GUI library for building user interfaces.

[0325] 2. System Processing Overview

[0326] The server first collects past installation increase data from a database and uses a machine learning algorithm to predict future installation increases based on this data. Based on the prediction results, it creates a list of equipment to be installed in the next year, obtains resource information (power capacity, cooling capacity, available space), and optimally allocates equipment to each data center.

[0327] When a user logs into the system, the camera captures the user's face, and the DeepFace library is used for emotion recognition. If the user is stressed, Tkinter is used to simplify the interface and improve ease of use.

[0328] 3. Specific Examples

[0329] The user logs into the system, and based on data from the past three years, it predicts that 30 robots will be needed for the next year. The server retrieves resource information from the database and appropriately allocates 20 robots to data center 1 and 10 robots to data center 2 based on the required resources.

[0330] The system captures the user's face through the camera and recognizes that the user is experiencing stress. In this case, the system improves user experience by simplifying the interface and adjusting it to display only essential information.

[0331] Example of a prompt

[0332] "Using data showing that the number of robots deployed has increased from 20 to 25 to 30 over the past three years, predict the number of robots needed for the next year. Additionally, create a program that recognizes user emotions and simplifies the interface if the user is experiencing stress."

[0333] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0334] Program processing steps

[0335] Step 1:

[0336] The server collects historical installation growth data from the database. In this step, it queries the database to retrieve installation records for the past several years (e.g., the past three years). The input is the installation growth data from the database, and the output is a dataset that uses this data to be passed to the next step. Specifically, the server issues an SQL query to retrieve the historical installation growth data in list format.

[0337] Step 2:

[0338] The server uses a machine learning algorithm based on the collected data to predict future installation increases. In this step, a model is trained using a linear regression model from scikit-learn, for example, to predict the installation increase needed for the next year. The input is past installation increase data, and the output is the predicted installation increase. Specifically, the server fits the data to the model and calculates the installation increase for the next year.

[0339] Step 3:

[0340] The server creates a list of equipment to be installed based on the predicted increase in capacity. This step lists the equipment to be installed in the next fiscal year according to the predicted increase in capacity. The input is the predicted increase in capacity, and the output is the list of equipment to be installed. Specifically, the server generates a list detailing the equipment to be installed in the next fiscal year.

[0341] Step 4:

[0342] The server retrieves data center resource information (power capacity, cooling capacity, available space). In this step, it issues queries to the facility management system to obtain the latest resource status. The input is query information, and the output is data center resource information. Specifically, the server accesses the facility management system and retrieves resource information for each facility.

[0343] Step 5:

[0344] The server compares the requirements of the equipment to be installed with the resources of the data center and allocates the equipment to the appropriate data center. In this step, the requirements of each piece of equipment are matched with the resource information of the data center to verify that the resources are adequately met. The input is a list of the equipment to be installed and resource information, and the output is the equipment allocation result. Specifically, the server calculates the resources required for each piece of equipment and allocates them to the optimal data center.

[0345] Step 6:

[0346] The user logs into the system. In this step, the user enters appropriate authentication information and is granted access to the system. The input is the user's authentication information, and the output is a notification of successful or unsuccessful login to the system. Specifically, the terminal provides a login screen and sends the user's authentication information to the server.

[0347] Step 7:

[0348] The server captures the user's face image via the camera and performs emotion analysis using the DeepFace library to recognize the user's emotions. In this step, the user's emotions are identified based on the video captured by the camera. The input is the captured face image, and the output is the identified emotion data. Specifically, the terminal activates the camera and passes the acquired face image to the emotion recognition algorithm.

[0349] Step 8:

[0350] The server adjusts the system's user interface based on emotional data. In this step, the interface is simplified when the user is stressed and more detailed when they are satisfied. The input is emotional data, and the output is the adjusted user interface. Specifically, the server changes the interface layout and functionality according to the user's emotional state.

[0351] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0352] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0353] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0354] [Second Embodiment]

[0355] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0356] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0357] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0358] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0359] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0360] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0361] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0362] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0363] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0364] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0365] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0366] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0367] This invention relates to a system that compares equipment to be installed in a data center with the resources available in the data center, and efficiently allocates the equipment. A specific embodiment of this system is described below.

[0368] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0369] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0370] Next, the server uses the acquired data to train a machine learning algorithm (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0371] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0372] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0373] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0374] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0375] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation.

[0376] The following describes the processing flow.

[0377] Step 1:

[0378] The user logs into the system. The user enters appropriate authentication information (such as username and password) and is granted access to the system.

[0379] Step 2:

[0380] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query against the database to retrieve installation records for the past three years.

[0381] Step 3:

[0382] The server uses the acquired installation data to train a machine learning model. For example, a linear regression model can be used to learn past installation trends.

[0383] Step 4:

[0384] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0385] Step 5:

[0386] The server generates a list of equipment to be installed in the next fiscal year based on predictions. This list includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0387] Step 6:

[0388] The server retrieves resource information from the data center. It issues queries to the facility management system to obtain information such as power capacity, cooling capacity, and available space for each data center.

[0389] Step 7:

[0390] Compare the requirements of the equipment where the servers are planned to be installed with the resources of the data center. Evaluate whether the requirements of each piece of equipment can be met with the current resources of the data center.

[0391] Step 8:

[0392] The server allocates equipment to each data center. Considering resource utilization efficiency, an allocation plan is developed to place equipment in the most suitable data center.

[0393] Step 9:

[0394] The server saves the allocation results to the database. The allocation plan is saved so that it can be referenced and modified later.

[0395] Step 10:

[0396] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0397] (Example 1)

[0398] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0399] As the amount of equipment planned for installation in data centers increases, efficiently managing resources and appropriately allocating equipment without excess or shortage becomes challenging. In particular, there is a need for a means to accurately understand future expansion forecasts and data center resource information, and to make optimal allocations. Furthermore, it is crucial that the system is easily accessible to users and that the status can be checked from a management screen.

[0400] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0401] In this invention, the server includes means for a user to enter authentication information and log in to the system; means for collecting past installation increase data; means for predicting future installation increases using a machine learning algorithm; means for creating a list of equipment to be installed based on the predicted increase; means for obtaining data center resource information; means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center; and means for saving the allocation results to a database and notifying the user of that information. This makes it possible to maximize resource utilization efficiency and realize a system that is highly convenient for users.

[0402] A "user" refers to an individual or organization that accesses and operates a system.

[0403] "Authentication information" refers to information used to identify a user and verify their access rights to the system, such as a user ID and password.

[0404] "Logging in" refers to the process of accessing and making available a system using authentication credentials.

[0405] A "server" refers to a computer system that performs tasks such as data processing and resource management.

[0406] "Installation increase data" refers to records of equipment newly installed in data centers in the past.

[0407] A "machine learning algorithm" refers to a statistical method used to analyze data and make predictions about future trends.

[0408] The "list of equipment to be installed" refers to a list of equipment that is scheduled to be installed in the future.

[0409] A "data center" refers to a facility where computers and other related equipment are installed.

[0410] "Resource information" refers to management information such as power capacity, cooling capacity, and available space within a data center.

[0411] "Equipment requirements" refer to the specific conditions such as power, cooling, and space required by the equipment to be installed.

[0412] "Comparison" refers to the process of matching the requirements of the equipment to be installed with the resource information of the data center and evaluating their suitability.

[0413] "Allocation" refers to the process of deciding where to place the equipment to be installed in the most appropriate data center.

[0414] A "database" refers to an information system that systematically manages large amounts of data and facilitates searching and updating.

[0415] "Notification" refers to the act of a system communicating information to a user.

[0416] A "facility management system" refers to a software system used to manage the status of resources and equipment within a data center.

[0417] A "resource allocation plan" refers to a detailed plan for efficiently using resources within a data center and arranging equipment accordingly.

[0418] This invention relates to a system for efficiently allocating equipment to be installed in a data center. This system enables users to optimize resource management with simple operations and formulate an appropriate equipment placement plan based on predictions.

[0419] First, the user logs into the system. The user enters appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen. The authentication process uses the user ID and password, which the server verifies against the database.

[0420] Next, the server collects past installation increase data. Specifically, the server issues queries to the database to extract past installation records. An example query is "SELECT FROM InstallationRecords WHERE Year >= 2019;". This data is temporarily stored in the server's memory.

[0421] After collecting historical data, the server uses a machine learning algorithm to predict future increases in the number of installations. The server builds and trains a linear regression model using machine learning libraries such as scikit-learn. The server uses the trained model to make predictions and generates a list of planned installations for the next year based on the results.

[0422] Next, the server retrieves resource information from the data center. The server issues a query to the facility management system to obtain the latest resource status. An example query is "SELECT FROM ResourceStatus;". This resource information is also temporarily stored in the server's memory.

[0423] The server matches the requirements of the equipment to be installed with the data center's resource information. It extracts the requirements for each piece of equipment (e.g., power, cooling, space) and compares them with the retrieved resource information. This verifies that resources are adequately met and helps develop an efficient resource allocation plan.

[0424] As a concrete example, based on records showing an increase of 20, 25, and 30 servers over the past three years, we predict that 35 servers will be needed in the next fiscal year. Subsequently, we obtain resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, available space 50 racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, available space 40 racks). If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, we decide to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0425] Finally, the server saves the allocation results to the database. The server then notifies the user of this information, and the user can check the allocation results through the system's administration screen. This enables optimal resource management and efficient operation.

[0426] An example of a prompt message is: "Train a linear regression model using installation data from the past three years to predict next year's server installation plan. Also, obtain the latest resource information for the data center and develop a deployment plan to optimally allocate equipment."

[0427] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0428] Step 1:

[0429] The user logs into the system.

[0430] The user accesses the system and enters authentication information (e.g., user ID and password). The server verifies this entered authentication information against the database. If authentication is successful, the server starts a session for the user and grants access to the administration screen. The input is the user ID and password, and the output is the authentication session.

[0431] Step 2:

[0432] The server collects past installation increase data.

[0433] The server issues an SQL query to the database to extract past installation records. Specifically, it executes the query "SELECT FROM InstallationRecords WHERE Year >= 2019;". The server temporarily stores the retrieved data in memory. The input is a query for installation increase data, and the output is past installation record data.

[0434] Step 3:

[0435] The server uses a machine learning algorithm to predict future increases in installation numbers.

[0436] The server loads machine learning libraries such as scikit-learn and builds a linear regression model using historical installation data. Next, it trains the model to predict future installation increases. The input is historical installation records, and the output is the predicted installation increase for the next year.

[0437] Step 4:

[0438] The server creates a list of equipment scheduled for installation in the next fiscal year.

[0439] The server creates a list of planned equipment installations for the next fiscal year based on the predicted increase in installations. This generates a list of specific equipment to be installed. The input is the predicted increase in installations, and the output is the list of planned equipment installations for the next fiscal year.

[0440] Step 5:

[0441] The server retrieves resource information from the data center.

[0442] The server issues an SQL query to the equipment management system to retrieve the latest resource information. Specifically, it executes the query "SELECT FROM ResourceStatus;". The server temporarily stores this information in memory. The input is the query for resource information, and the output is the latest resource information data.

[0443] Step 6:

[0444] Compare the requirements of the equipment where the server will be installed with the resources of the data center.

[0445] The server loads a list of planned equipment and resource information, and compares the requirements (e.g., power, cooling, space) and resources for each. This verifies that the resources are adequately met. The input is the list of planned equipment and resource information, and the output is a resource allocation plan.

[0446] Step 7:

[0447] The server allocates the equipment to the appropriate data center.

[0448] Based on the comparison results, the server allocates the equipment to be installed in each data center. This ensures optimal resource utilization. The server saves the allocation results to a database and formulates a deployment plan. The input is the resource allocation plan, and the output is the allocation results and the deployment plan.

[0449] Step 8:

[0450] The server notifies the user of the allocation result.

[0451] The server notifies the user of the allocation results, making them available for viewing from the system's administration screen. This allows users to achieve optimal resource management. The input is the allocation results, and the output is the notification to the user.

[0452] (Application Example 1)

[0453] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0454] There is a need to simultaneously address two different challenges: efficiently managing data center resources and optimizing parking locations for autonomous vehicles. This requires streamlining complex tasks such as data center equipment installation planning, vehicle resource management, and parking location selection, thereby reducing costs and improving operational efficiency.

[0455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0456] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for collecting vehicle sensor data and evaluating parking spaces, and means for comparing vehicle resources with the conditions of the parking space and selecting the optimal parking location. This enables efficient management of data center resources and optimization of parking location selection for autonomous vehicles.

[0457] "Installation increase data" refers to data on the historical increase in the number of equipment installations in data centers and other related facilities.

[0458] A "machine learning algorithm" is a mathematical method that learns patterns from past data to make predictions and decisions about the future.

[0459] The "List of Equipment to be Installed" is a list of equipment that is planned to be installed in the data center in the future, based on the predicted increase in installations.

[0460] "Data center resource information" refers to information about the current state of resources available to the data center, such as power capacity, cooling capacity, and available space.

[0461] "Equipment requirements" refer to the conditions such as power, cooling, and space necessary for the equipment to be installed to operate normally.

[0462] "Sensor data" refers to information such as battery level, internal temperature, and available space collected by sensors installed in autonomous vehicles.

[0463] "Parking space evaluation" is the process of using the vehicle's cameras and sensors to determine how available or appropriate a parking space is at present.

[0464] An "optimal parking spot" is the most suitable parking location for a vehicle, based on its resource information and the conditions of the parking space.

[0465] This invention provides a system that integrates data center resource management and the optimization of parking locations for autonomous vehicles. This system includes the following means:

[0466] First, the server collects historical installation growth data. This data is obtained from installation records stored in a database for the past several years. The server queries the database to extract historical installation records.

[0467] Next, the server uses the acquired data to train a machine learning algorithm. For example, it uses a linear regression model to predict future increases in the number of installations. Based on the prediction results, it generates a list of equipment scheduled for installation in the following year.

[0468] The server also retrieves resource information from the data center. This resource information is obtained from the data center's facility management system. Queries are issued to the facility management system to retrieve the latest resource status.

[0469] Next, the server compares the requirements of the equipment to be installed (e.g., power consumption, cooling requirements, installation space) with the resources of the data center to ensure that the resources are adequately met. Then, it allocates the equipment to the appropriate data center.

[0470] Furthermore, the server collects data from the vehicle's sensors, including battery level, internal temperature, and available space. It also uses data from the vehicle's cameras and sensors to assess the availability of parking spaces.

[0471] The server uses the collected data to compare the vehicle's resources with the conditions of the parking space and select the optimal parking location. A linear regression model is applied to this process to predict the most suitable parking location for the vehicle.

[0472] The hardware used includes cameras, temperature sensors, space sensors, and servers mounted on the autonomous vehicle. The software used includes OpenCV for data processing, NumPy for data analysis, and scikit-learn for machine learning models.

[0473] As a concrete example, real-time data is collected from in-vehicle cameras and sensors, and this data is processed using OpenCV. For instance, to evaluate the availability of parking spaces, camera data is binarized and the number of white pixels is counted. Based on sensor data (battery level, internal temperature, available space), basic conditions are evaluated, and the optimal parking location is selected using a linear regression model.

[0474] An example of a prompt message is: "Analyze the availability of parking spaces and recommend the best parking spot considering the vehicle's battery level, interior temperature, and available space."

[0475] This will enable more efficient resource management in data centers and optimize the selection of parking locations for autonomous vehicles.

[0476] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0477] Step 1:

[0478] The server collects historical installation data from the database. First, it issues a query to the database to extract past installation records. This data includes the quantity of equipment installed over the past few years, the installation date and time, and the installation location. Using the configured query as input, the server obtains historical installation data as output.

[0479] Step 2:

[0480] The server trains a machine learning algorithm using collected installation increase data. It applies a linear regression model to learn trends for predicting future installation increases. Historical installation data is used as input, and the optimal regression model is output through computation.

[0481] Step 3:

[0482] The server creates a list of equipment to be installed based on the predicted increase in capacity. Based on the prediction results, it generates a list of equipment expected to be installed in the next fiscal year. Machine learning prediction results are used as input, and a list of equipment to be installed is generated as output.

[0483] Step 4:

[0484] The server retrieves data center resource information. This is done by querying the facility management system to obtain the latest information on power capacity, cooling capacity, and available space. A query is set as the input, and data center resource information is obtained as the output.

[0485] Step 5:

[0486] The server compares the requirements of the equipment to be installed (power consumption, cooling requirements, installation space) with the resource information of the data center. It checks whether each piece of equipment meets the requirements and allocates the equipment to the appropriate data center. The equipment requirements and data center resource information are used as input, and the output is the allocation result of the optimal installation location.

[0487] Step 6:

[0488] The server collects sensor data (battery level, internal temperature, available space) from the autonomous vehicle. It acquires real-time data from each sensor and takes the sensor data as input. Status information for each sensor is obtained as output.

[0489] Step 7:

[0490] The server evaluates the availability of parking spaces based on data from the vehicle's cameras and sensors. It uses OpenCV to process camera data and evaluate available spaces. Camera data is used as input, and the evaluation result for available spaces is obtained as output.

[0491] Step 8:

[0492] The server compares vehicle resources and parking space conditions based on collected data to select the optimal parking location. A linear regression model is used to calculate a parking location evaluation score. Sensor data and the evaluation results of available spaces are used as input, and the output is the selection result of the optimal parking location.

[0493] Step 9:

[0494] The server saves the allocation results and parking location selection results to a database and notifies the user of this information. It records the allocation results and optimal parking location information in the database and notifies the user. Allocation results and selection results are used as input, and user notifications are generated as output.

[0495] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0496] This invention combines a system that compares the equipment to be installed in a data center with the resources available in the data center to efficiently allocate the equipment, with an emotion engine that recognizes user emotions. A specific embodiment of this system is described below.

[0497] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0498] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0499] Next, the server uses the acquired data to train a machine learning model (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0500] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0501] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0502] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0503] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's voice, facial expressions, and input content to identify the user's emotional state. The server analyzes the emotional data obtained from the emotion engine and adjusts the system's display interface and operation flow based on the results. For example, if the user is stressed, the system will either provide a simpler interface or enhance its assistance functions.

[0504] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0505] Next, the emotion engine recognizes the user's emotional state. For example, if it detects that the user is feeling stressed during an interaction, the server simplifies the interface and adjusts it to allow the user to interact more smoothly. Furthermore, if the emotion engine is satisfied, it provides detailed resource allocation options to allow the user to engage more deeply.

[0506] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation. The combination with the emotion engine improves the user experience and reduces stress and frustration.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The user logs into the system. The user enters appropriate authentication information, such as a username and password, to obtain permission to access the system.

[0510] Step 2:

[0511] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query to extract data in order to retrieve installation records for the past three years.

[0512] Step 3:

[0513] The server uses the acquired installation data to train a machine learning model (e.g., a linear regression model). This allows the model to learn past data patterns and prepare to predict future increases in installation numbers.

[0514] Step 4:

[0515] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0516] Step 5:

[0517] The server generates a list of equipment to be installed in the next fiscal year based on predictions. Specifically, it creates a list that includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0518] Step 6:

[0519] The server retrieves data center resource information (e.g., power capacity, cooling capacity, available space). It then issues queries to the facility management system to obtain the latest resource status.

[0520] Step 7:

[0521] The system compares the requirements of the equipment where the servers are planned to be installed with the resources of the data center. It evaluates whether the requirements of each piece of equipment can be met with the current resources of the data center and determines the degree of suitability.

[0522] Step 8:

[0523] The server allocates equipment to each data center. It selects data centers that maximize resource utilization efficiency and can accommodate the necessary equipment without excess or shortage. It then develops an allocation plan and places the equipment in the corresponding data centers.

[0524] Step 9:

[0525] The server saves the allocation results to the database. The allocation plan is saved to the database so that it can be referenced and modified later.

[0526] Step 10:

[0527] The emotion engine recognizes the user's emotional state. It analyzes the voice, facial expressions, and input content the user provides during operation to identify stress levels and satisfaction levels.

[0528] Step 11:

[0529] The server adjusts the system's display interface and operation flow based on data obtained from the emotion engine. For example, if the system detects that the user is stressed, it simplifies the interface and enhances assistance features.

[0530] Step 12:

[0531] The server uses the sentiment engine's results to inform the user of the allocation decision in the most optimal way. For example, when the user is satisfied, it provides detailed resource allocation options, allowing the user to be more deeply involved.

[0532] Step 13:

[0533] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0534] In this way, the system utilizes an emotion engine to operate in accordance with the user's emotional state, achieving optimal resource management and efficient data center utilization.

[0535] (Example 2)

[0536] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0537] Ensuring consistency between the equipment planned for installation in the data center and the actual resources available, and efficiently allocating equipment, are crucial requirements. Furthermore, improving system usability and reducing user stress are also important challenges.

[0538] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0539] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for obtaining data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means including an emotion engine that recognizes user emotions, and means for analyzing emotion data obtained from the emotion engine and adjusting the system interface and operation flow. This enables efficient allocation of equipment, improved user operability, and reduced stress.

[0540] "Past installation increase data" refers to record data regarding equipment installed in data centers in the past and the increase in that number.

[0541] A "machine learning algorithm" is a computational method used to learn patterns and rules from data and perform predictions and classifications.

[0542] The "List of Equipment to be Installed" is information that shows a list of equipment that is planned to be installed in the data center in the next fiscal year.

[0543] "Data center resource information" refers to information about the resources necessary for installing equipment in a data center, such as power capacity, cooling capacity, and available space.

[0544] "Requirements for equipment to be installed" refers to the resource requirements, such as power, cooling, and space, that the equipment to be installed in the data center will need.

[0545] An "emotion engine" is a system that analyzes and identifies a user's emotional state based on their voice, facial expressions, input content, and other factors.

[0546] "Means for adjusting the interface and operation flow" refers to functions that change and optimize the system's display screen and operation procedures based on the user's emotional state.

[0547] "Allocation results" refer to information regarding the plan for efficiently placing equipment in each data center and the results thereof.

[0548] This invention provides a system that efficiently compares equipment to be installed in a data center with the resources of the data center and allocates the equipment optimally. Furthermore, it incorporates an emotion engine that recognizes user emotions to improve usability.

[0549] First, the user logs into the system. The user uses a browser or a dedicated application to enter appropriate authentication information (ID and password). The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the user can access the administration screen.

[0550] Next, the server collects historical installation increase data. This data is obtained from equipment installation records for the past several years stored in the database. An SQL query is executed to extract the data in a format such as "SELECT FROM installation_records WHERE year BETWEEN 2019 AND 2021;".

[0551] Based on the acquired data, the server trains a linear regression model using a machine learning library (e.g., Scikit-learn). This model is used to predict future increases in the number of installations. For example, if past installation data shows 20, 25, and 30, it can predict 35 for the following year.

[0552] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year. This equipment list is saved in JSON or CSV format and used for future management.

[0553] Next, the server retrieves resource information for the data center. This resource information includes power capacity, cooling capacity, and available space. The server issues a query to the facility management system and retrieves the data in a format such as "SELECT FROM resource WHERE datacenterID = 1;".

[0554] Based on the acquired resource information, the server compares the requirements of the planned equipment (power, cooling, space) with the resources of the data center. For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server will evaluate the resources of each data center.

[0555] Based on the comparison results, the servers allocate equipment to each data center. The allocation results are formulated as a specific deployment plan, such as "20 servers in Data Center 1 and 15 servers in Data Center 2." This plan is stored in a database and used for future implementation.

[0556] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The server invokes the emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input. Based on the resulting emotion data, it adjusts the interface and operation flow.

[0557] For example, if the server detects that a user is experiencing stress while operating the system, it can simplify the interface and streamline the operation. Furthermore, if the user is satisfied, it can provide more detailed resource allocation options.

[0558] As a result, this system achieves efficient allocation of equipment, improved user experience, and reduced stress.

[0559] A concrete example would be a user logging into the system and seeing records showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the system predicts that 35 servers will be needed in the next fiscal year. Next, it obtains resource information for each data center and decides to allocate 20 servers to data center 1 and 15 servers to data center 2.

[0560] Furthermore, the emotion engine detects when the user is experiencing stress during their interaction, and the server provides a simple interface. In this way, the system's usability and the user experience are optimized.

[0561] An example of a prompt message for a generating AI model is, "Generate a list of servers to be installed in the next fiscal year and efficiently allocate them to each data center."

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1: User Login

[0564] Specific operation and input / output:

[0565] Users access the system using a browser or a dedicated application.

[0566] The user enters authentication information such as their ID and password.

[0567] Input: User authentication information (ID and password)

[0568] The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the server grants the user access to the administration screen.

[0569] Output: Authentication success / failure result and access rights to the administration screen

[0570] Step 2: Collecting past installation increase data

[0571] Specific operation and input / output:

[0572] The server executes SQL queries against the database to retrieve equipment installation records for the past several years.

[0573] Input: Installation records stored in the database

[0574] For example, execute a query like "SELECT FROM Installation Records WHERE Year BETWEEN 2019 AND 2021;".

[0575] Output: Past installation increase data

[0576] Step 3: Training and predicting machine learning models

[0577] Specific operation and input / output:

[0578] The server uses the collected data to train a linear regression model using a machine learning library (e.g., Scikit-learn).

[0579] Input: Past installation increase data

[0580] The server inputs new data into the trained model and predicts the increase in equipment installations for the following year.

[0581] Example: If past installation data shows 20, 25, and 30, then the forecast for the next year is 35.

[0582] Output: Predicted increase in the number of installations for the next fiscal year

[0583] Step 4: Generating the equipment list for the next fiscal year

[0584] Specific operation and input / output:

[0585] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year.

[0586] Input: Predicted increase in the number of installations for the next fiscal year

[0587] This device list is saved in JSON or CSV format.

[0588] Output: List of equipment scheduled for installation in the next fiscal year

[0589] Step 5: Obtain data center resource information

[0590] Specific operation and input / output:

[0591] The server issues a query to the data center's facility management system to retrieve resource information.

[0592] Input: Query to retrieve resource information

[0593] For example, execute the query "SELECT FROM resource WHERE datacenterID = 1;".

[0594] Output: Data center resource information (power capacity, cooling capacity, available space, etc.)

[0595] Step 6: Comparison of requirements and resources for the equipment to be installed.

[0596] Specific operation and input / output:

[0597] The server compares the requirements of each device with the resource information of the data center.

[0598] Input: Requirements for the equipment to be installed (power, cooling, space), data center resource information

[0599] For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the resource information is evaluated against those requirements.

[0600] Output: Resource evaluation results

[0601] Step 7: Develop equipment allocation and placement plans.

[0602] Specific operation and input / output:

[0603] Based on the comparison results, the servers efficiently allocate equipment to each data center.

[0604] Input: Resource evaluation results

[0605] The allocation plan is then specified, for example, "20 units in Data Center 1, and 15 units in Data Center 2."

[0606] The generated deployment plan is saved in the database.

[0607] Output: Layout plan

[0608] Step 8: User emotion recognition by the emotion engine

[0609] Specific operation and input / output:

[0610] The server calls an emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input.

[0611] Input: User's voice, facial expressions, and input content

[0612] The server identifies the user's emotional state (e.g., stress, satisfaction) from the analysis results.

[0613] Output: Sentiment data

[0614] Step 9: Adjusting the Interface

[0615] Specific operation and input / output:

[0616] The server adjusts the interface and operation flow based on user sentiment data.

[0617] Input: Sentiment data

[0618] For example, if a user is experiencing stress, provide a simplified interface.

[0619] Output: Adjusted interface, operation flow

[0620] Step 10: Saving and notifying results

[0621] Specific operation and input / output:

[0622] The server saves the final allocation results and user actions to the database.

[0623] Input: Final allocation result, user actions

[0624] The server notifies the user's terminal that new information is available.

[0625] Output: Saved data, notification messages

[0626] (Application Example 2)

[0627] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0628] In data centers, expanding equipment and managing resources are crucial for efficient operation and optimal resource allocation. However, performing these tasks manually is complex and time-consuming, and can lead to operational errors and decreased efficiency, especially depending on the user's emotional state. Therefore, there is a need for a system that uses historical data for prediction, automated resource allocation, and adapts the user interface according to the user's emotional state.

[0629] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0630] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for recognizing the user's emotions, and means for adjusting the system's operating interface based on the user's emotions. This enables efficient and appropriate equipment allocation and flexible interface adjustment according to the user's emotional state.

[0631] "Installation increase data" refers to records of increases or decreases in the number of devices and equipment installed in the past.

[0632] A "machine learning algorithm" is a mathematical method that learns patterns from data and uses those patterns to make future predictions and classifications.

[0633] The "list of equipment to be installed" is a list of equipment and facilities that are planned to be installed in the future.

[0634] A "data center" is a facility that centrally houses a large number of computers and storage devices for data storage and processing.

[0635] "Resource information" refers to information regarding the utilization status of resources in a data center, such as power capacity, cooling capacity, and available space.

[0636] "Equipment requirements" refer to the conditions and specifications, such as power, cooling, and space, necessary for the operation of equipment or facilities.

[0637] "User emotions" refer to the psychological and physiological state and mood of the user operating the system.

[0638] An "operation interface" refers to the screens and input methods that users use to interact with and operate a system.

[0639] "Emotion recognition means" refers to technologies and devices that analyze a user's voice and facial expressions to identify their emotional state.

[0640] "Means of allocating equipment to appropriate data centers" refers to methods or algorithms for placing equipment in data centers that meet the requirements of the equipment to be installed.

[0641] "Means of adjusting the system's operating interface based on emotions" refers to methods and technologies for changing the operating screen or input method in consideration of the user's emotional state.

[0642] This invention is a system that improves the efficiency of equipment installation and user experience in data centers. The system collects historical installation growth data and uses machine learning algorithms to predict future installation growth. Based on the predicted growth, it creates a list of equipment to be installed and allocates equipment to appropriate data centers by comparing data center resource information with equipment requirements. Furthermore, it includes a function to recognize user emotions and adjust the operating interface based on those emotions.

[0643] 1. Hardware and software used

[0644] The system is implemented using the following hardware and software:

[0645] server:

[0646] Computational resources for data collection and machine learning.

[0647] Connect to the database and retrieve past installation increase data.

[0648] Perform calculations to formulate equipment allocation and placement plans.

[0649] camera:

[0650] A webcam that captures the user's facial image for emotion recognition.

[0651] DeepFace:

[0652] An emotion recognition library for analyzing user emotions.

[0653] scikit-learn:

[0654] A library for predicting future increases in installation numbers using machine learning algorithms (linear regression models).

[0655] Tkinter:

[0656] A GUI library for building user interfaces.

[0657] 2. System Processing Overview

[0658] The server first collects past installation increase data from a database and uses a machine learning algorithm to predict future installation increases based on this data. Based on the prediction results, it creates a list of equipment to be installed in the next year, obtains resource information (power capacity, cooling capacity, available space), and optimally allocates equipment to each data center.

[0659] When a user logs into the system, the camera captures the user's face, and the DeepFace library is used for emotion recognition. If the user is stressed, Tkinter is used to simplify the interface and improve ease of use.

[0660] 3. Specific examples

[0661] The user logs into the system, and based on data from the past three years, it predicts that 30 robots will be needed for the next year. The server retrieves resource information from the database and appropriately allocates 20 robots to data center 1 and 10 robots to data center 2 based on the required resources.

[0662] The system captures the user's face through the camera and recognizes that the user is experiencing stress. In this case, the system improves user experience by simplifying the interface and adjusting it to display only essential information.

[0663] Example of a prompt

[0664] "Using data showing that the number of robots deployed has increased from 20 to 25 to 30 over the past three years, predict the number of robots needed for the next year. Additionally, create a program that recognizes user emotions and simplifies the interface if the user is experiencing stress."

[0665] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0666] Program processing steps

[0667] Step 1:

[0668] The server collects historical installation growth data from the database. In this step, it queries the database to retrieve installation records for the past several years (e.g., the past three years). The input is the installation growth data from the database, and the output is a dataset that uses this data to be passed to the next step. Specifically, the server issues an SQL query to retrieve the historical installation growth data in list format.

[0669] Step 2:

[0670] The server uses a machine learning algorithm based on the collected data to predict future installation increases. In this step, a model is trained using a linear regression model from scikit-learn, for example, to predict the installation increase needed for the next year. The input is past installation increase data, and the output is the predicted installation increase. Specifically, the server fits the data to the model and calculates the installation increase for the next year.

[0671] Step 3:

[0672] The server creates a list of equipment to be installed based on the predicted increase in capacity. This step lists the equipment to be installed in the next fiscal year according to the predicted increase in capacity. The input is the predicted increase in capacity, and the output is the list of equipment to be installed. Specifically, the server generates a list detailing the equipment to be installed in the next fiscal year.

[0673] Step 4:

[0674] The server retrieves data center resource information (power capacity, cooling capacity, available space). In this step, it issues queries to the facility management system to obtain the latest resource status. The input is query information, and the output is data center resource information. Specifically, the server accesses the facility management system and retrieves resource information for each facility.

[0675] Step 5:

[0676] The server compares the requirements of the equipment to be installed with the resources of the data center and allocates the equipment to the appropriate data center. In this step, the requirements of each piece of equipment are matched with the resource information of the data center to verify that the resources are adequately met. The input is a list of the equipment to be installed and resource information, and the output is the equipment allocation result. Specifically, the server calculates the resources required for each piece of equipment and allocates them to the optimal data center.

[0677] Step 6:

[0678] The user logs into the system. In this step, the user enters appropriate authentication information and is granted access to the system. The input is the user's authentication information, and the output is a notification of successful or unsuccessful login to the system. Specifically, the terminal provides a login screen and sends the user's authentication information to the server.

[0679] Step 7:

[0680] The server captures the user's face image via the camera and performs emotion analysis using the DeepFace library to recognize the user's emotions. In this step, the user's emotions are identified based on the video captured by the camera. The input is the captured face image, and the output is the identified emotion data. Specifically, the terminal activates the camera and passes the acquired face image to the emotion recognition algorithm.

[0681] Step 8:

[0682] The server adjusts the system's user interface based on emotional data. In this step, the interface is simplified when the user is stressed and more detailed when they are satisfied. The input is emotional data, and the output is the adjusted user interface. Specifically, the server changes the interface layout and functionality according to the user's emotional state.

[0683] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0684] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0685] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0686] [Third Embodiment]

[0687] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0688] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0689] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0690] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0691] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0692] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0693] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0694] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0695] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0696] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0697] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0698] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0699] This invention relates to a system that compares equipment to be installed in a data center with the resources available in the data center, and efficiently allocates the equipment. A specific embodiment of this system is described below.

[0700] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0701] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0702] Next, the server uses the acquired data to train a machine learning algorithm (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0703] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0704] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0705] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0706] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0707] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation.

[0708] The following describes the processing flow.

[0709] Step 1:

[0710] The user logs into the system. The user enters appropriate authentication information (such as username and password) and is granted access to the system.

[0711] Step 2:

[0712] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query against the database to retrieve installation records for the past three years.

[0713] Step 3:

[0714] The server uses the acquired installation data to train a machine learning model. For example, a linear regression model can be used to learn past installation trends.

[0715] Step 4:

[0716] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0717] Step 5:

[0718] The server generates a list of equipment to be installed in the next fiscal year based on predictions. This list includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0719] Step 6:

[0720] The server retrieves resource information from the data center. It issues queries to the facility management system to obtain information such as power capacity, cooling capacity, and available space for each data center.

[0721] Step 7:

[0722] Compare the requirements of the equipment where the servers are planned to be installed with the resources of the data center. Evaluate whether the requirements of each piece of equipment can be met with the current resources of the data center.

[0723] Step 8:

[0724] The server allocates equipment to each data center. Considering resource utilization efficiency, an allocation plan is developed to place equipment in the most suitable data center.

[0725] Step 9:

[0726] The server saves the allocation results to the database. The allocation plan is saved so that it can be referenced and modified later.

[0727] Step 10:

[0728] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0729] (Example 1)

[0730] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0731] As the amount of equipment planned for installation in data centers increases, efficiently managing resources and appropriately allocating equipment without excess or shortage becomes challenging. In particular, there is a need for a means to accurately understand future expansion forecasts and data center resource information, and to make optimal allocations. Furthermore, it is crucial that the system is easily accessible to users and that the status can be checked from a management screen.

[0732] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0733] In this invention, the server includes means for a user to enter authentication information and log in to the system; means for collecting past installation increase data; means for predicting future installation increases using a machine learning algorithm; means for creating a list of equipment to be installed based on the predicted increase; means for obtaining data center resource information; means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center; and means for saving the allocation results to a database and notifying the user of that information. This makes it possible to maximize resource utilization efficiency and realize a system that is highly convenient for users.

[0734] A "user" refers to an individual or organization that accesses and operates a system.

[0735] "Authentication information" refers to information used to identify a user and verify their access rights to the system, such as a user ID and password.

[0736] "Logging in" refers to the process of accessing and making available a system using authentication credentials.

[0737] A "server" refers to a computer system that performs tasks such as data processing and resource management.

[0738] "Installation increase data" refers to records of equipment newly installed in data centers in the past.

[0739] A "machine learning algorithm" refers to a statistical method used to analyze data and make predictions about future trends.

[0740] The "list of equipment to be installed" refers to a list of equipment that is scheduled to be installed in the future.

[0741] A "data center" refers to a facility where computers and other related equipment are installed.

[0742] "Resource information" refers to management information such as power capacity, cooling capacity, and available space within a data center.

[0743] "Equipment requirements" refer to the specific conditions such as power, cooling, and space required by the equipment to be installed.

[0744] "Comparison" refers to the process of matching the requirements of the equipment to be installed with the resource information of the data center and evaluating their suitability.

[0745] "Allocation" refers to the process of deciding where to place the equipment to be installed in the most appropriate data center.

[0746] A "database" refers to an information system that systematically manages large amounts of data and facilitates searching and updating.

[0747] "Notification" refers to the act of a system communicating information to a user.

[0748] A "facility management system" refers to a software system used to manage the status of resources and equipment within a data center.

[0749] A "resource allocation plan" refers to a detailed plan for efficiently using resources within a data center and arranging equipment accordingly.

[0750] This invention relates to a system for efficiently allocating equipment to be installed in a data center. This system enables users to optimize resource management with simple operations and formulate an appropriate equipment placement plan based on predictions.

[0751] First, the user logs into the system. The user enters appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen. The authentication process uses the user ID and password, which the server verifies against the database.

[0752] Next, the server collects past installation increase data. Specifically, the server issues queries to the database to extract past installation records. An example query is "SELECT FROM InstallationRecords WHERE Year >= 2019;". This data is temporarily stored in the server's memory.

[0753] After collecting historical data, the server uses a machine learning algorithm to predict future increases in the number of installations. The server builds and trains a linear regression model using machine learning libraries such as scikit-learn. The server uses the trained model to make predictions and generates a list of planned installations for the next year based on the results.

[0754] Next, the server retrieves resource information from the data center. The server issues a query to the facility management system to obtain the latest resource status. An example query is "SELECT FROM ResourceStatus;". This resource information is also temporarily stored in the server's memory.

[0755] The server matches the requirements of the equipment to be installed with the data center's resource information. It extracts the requirements for each piece of equipment (e.g., power, cooling, space) and compares them with the retrieved resource information. This verifies that resources are adequately met and helps develop an efficient resource allocation plan.

[0756] As a concrete example, based on records showing an increase of 20, 25, and 30 servers over the past three years, we predict that 35 servers will be needed in the next fiscal year. Subsequently, we obtain resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks). If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, we decide to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0757] Finally, the server saves the allocation results to the database. The server then notifies the user of this information, and the user can check the allocation results through the system's administration screen. This enables optimal resource management and efficient operation.

[0758] An example of a prompt message is: "Train a linear regression model using installation data from the past three years to predict next year's server installation plan. Also, obtain the latest resource information for the data center and develop a deployment plan to optimally allocate equipment."

[0759] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0760] Step 1:

[0761] The user logs into the system.

[0762] The user accesses the system and enters authentication information (e.g., user ID and password). The server verifies this entered authentication information against the database. If authentication is successful, the server starts a session for the user and grants access to the administration screen. The input is the user ID and password, and the output is the authentication session.

[0763] Step 2:

[0764] The server collects past installation increase data.

[0765] The server issues an SQL query to the database to extract past installation records. Specifically, it executes the query "SELECT FROM InstallationRecords WHERE Year >= 2019;". The server temporarily stores the retrieved data in memory. The input is a query for installation increase data, and the output is past installation record data.

[0766] Step 3:

[0767] The server uses a machine learning algorithm to predict future increases in installation numbers.

[0768] The server loads machine learning libraries such as scikit-learn and builds a linear regression model using historical installation data. Next, it trains the model to predict future installation increases. The input is historical installation records, and the output is the predicted installation increase for the next year.

[0769] Step 4:

[0770] The server creates a list of equipment scheduled for installation in the next fiscal year.

[0771] The server creates a list of planned equipment installations for the next fiscal year based on the predicted increase in installations. This generates a list of specific equipment to be installed. The input is the predicted increase in installations, and the output is the list of planned equipment installations for the next fiscal year.

[0772] Step 5:

[0773] The server retrieves resource information from the data center.

[0774] The server issues an SQL query to the equipment management system to retrieve the latest resource information. Specifically, it executes the query "SELECT FROM ResourceStatus;". The server temporarily stores this information in memory. The input is the query for resource information, and the output is the latest resource information data.

[0775] Step 6:

[0776] Compare the requirements of the equipment where the server will be installed with the resources of the data center.

[0777] The server loads a list of planned equipment and resource information, and compares the requirements (e.g., power, cooling, space) and resources for each. This verifies that the resources are adequately met. The input is the list of planned equipment and resource information, and the output is a resource allocation plan.

[0778] Step 7:

[0779] The server allocates the equipment to the appropriate data center.

[0780] Based on the comparison results, the server allocates the equipment to be installed in each data center. This ensures optimal resource utilization. The server saves the allocation results to a database and formulates a deployment plan. The input is the resource allocation plan, and the output is the allocation results and the deployment plan.

[0781] Step 8:

[0782] The server notifies the user of the allocation result.

[0783] The server notifies the user of the allocation results, making them available for viewing from the system's administration screen. This allows users to achieve optimal resource management. The input is the allocation results, and the output is the notification to the user.

[0784] (Application Example 1)

[0785] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0786] There is a need to simultaneously address two different challenges: efficiently managing data center resources and optimizing parking locations for autonomous vehicles. This requires streamlining complex tasks such as data center equipment installation planning, vehicle resource management, and parking location selection, thereby reducing costs and improving operational efficiency.

[0787] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0788] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for collecting vehicle sensor data and evaluating parking spaces, and means for comparing vehicle resources with the conditions of the parking space and selecting the optimal parking location. This enables efficient management of data center resources and optimization of parking location selection for autonomous vehicles.

[0789] "Installation increase data" refers to data on the historical increase in the number of equipment installations in data centers and other related facilities.

[0790] A "machine learning algorithm" is a mathematical method that learns patterns from past data to make predictions and decisions about the future.

[0791] The "List of Equipment to be Installed" is a list of equipment that is planned to be installed in the data center in the future, based on the predicted increase in installations.

[0792] "Data center resource information" refers to information about the current state of resources available to the data center, such as power capacity, cooling capacity, and available space.

[0793] "Equipment requirements" refer to the conditions such as power, cooling, and space necessary for the equipment to be installed to operate normally.

[0794] "Sensor data" refers to information such as battery level, internal temperature, and available space collected by sensors installed in autonomous vehicles.

[0795] "Parking space evaluation" is the process of using the vehicle's cameras and sensors to determine how available or suitable a parking space is at present.

[0796] An "optimal parking spot" is the most suitable parking location for a vehicle, based on its resource information and the conditions of the parking space.

[0797] This invention provides a system that integrates data center resource management and optimization of parking locations for autonomous vehicles. This system includes the following means:

[0798] First, the server collects historical installation growth data. This data is obtained from installation records stored in a database for the past several years. The server queries the database to extract historical installation records.

[0799] Next, the server uses the acquired data to train a machine learning algorithm. For example, it uses a linear regression model to predict future increases in the number of installations. Based on the prediction results, it generates a list of equipment scheduled for installation in the following year.

[0800] The server also retrieves resource information from the data center. This resource information is obtained from the data center's facility management system. Queries are issued to the facility management system to retrieve the latest resource status.

[0801] Next, the server compares the requirements of the equipment to be installed (e.g., power consumption, cooling requirements, installation space) with the resources of the data center to ensure that the resources are adequately met. Then, it allocates the equipment to the appropriate data center.

[0802] Furthermore, the server collects data from the vehicle's sensors, including battery level, internal temperature, and available space. It also uses data from the vehicle's cameras and sensors to assess the availability of parking spaces.

[0803] The server uses the collected data to compare the vehicle's resources with the conditions of the parking space and select the optimal parking location. A linear regression model is applied to this process to predict the most suitable parking location for the vehicle.

[0804] The hardware used includes cameras, temperature sensors, space sensors, and servers mounted on the autonomous vehicle. The software used includes OpenCV for data processing, NumPy for data analysis, and scikit-learn for machine learning models.

[0805] As a concrete example, real-time data is collected from in-vehicle cameras and sensors, and this data is processed using OpenCV. For instance, to evaluate the availability of parking spaces, camera data is binarized and the number of white pixels is counted. Based on sensor data (battery level, internal temperature, available space), basic conditions are evaluated, and the optimal parking location is selected using a linear regression model.

[0806] An example of a prompt message is: "Analyze the availability of parking spaces and recommend the best parking spot considering the vehicle's battery level, interior temperature, and available space."

[0807] This will enable more efficient resource management in data centers and optimize the selection of parking locations for autonomous vehicles.

[0808] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0809] Step 1:

[0810] The server collects historical installation data from the database. First, it issues a query to the database to extract past installation records. This data includes the quantity of equipment installed over the past few years, the installation date and time, and the installation location. Using the configured query as input, the server obtains historical installation data as output.

[0811] Step 2:

[0812] The server trains a machine learning algorithm using collected installation increase data. It applies a linear regression model to learn trends for predicting future installation increases. Historical installation data is used as input, and the optimal regression model is output through computation.

[0813] Step 3:

[0814] The server creates a list of equipment to be installed based on the predicted increase in capacity. Based on the prediction results, it generates a list of equipment expected to be installed in the next fiscal year. Machine learning prediction results are used as input, and a list of equipment to be installed is generated as output.

[0815] Step 4:

[0816] The server retrieves data center resource information. This is done by querying the facility management system to obtain the latest information on power capacity, cooling capacity, and available space. A query is set as the input, and data center resource information is obtained as the output.

[0817] Step 5:

[0818] The server compares the requirements of the equipment to be installed (power consumption, cooling requirements, installation space) with the resource information of the data center. It checks whether each piece of equipment meets the requirements and allocates the equipment to the appropriate data center. The equipment requirements and data center resource information are used as input, and the output is the allocation result of the optimal installation location.

[0819] Step 6:

[0820] The server collects sensor data (battery level, internal temperature, available space) from the autonomous vehicle. It acquires real-time data from each sensor and takes the sensor data as input. Status information for each sensor is obtained as output.

[0821] Step 7:

[0822] The server evaluates the availability of parking spaces based on data from the vehicle's cameras and sensors. It uses OpenCV to process camera data and evaluate available spaces. Camera data is used as input, and the evaluation result for available spaces is obtained as output.

[0823] Step 8:

[0824] The server compares vehicle resources and parking space conditions based on collected data to select the optimal parking location. A linear regression model is used to calculate a parking location evaluation score. Sensor data and the evaluation results of available spaces are used as input, and the output is the selection result of the optimal parking location.

[0825] Step 9:

[0826] The server saves the allocation results and parking location selection results to a database and notifies the user of this information. It records the allocation results and optimal parking location information in the database and notifies the user. The allocation results and selection results are used as input, and the user notification is output.

[0827] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0828] This invention combines a system that compares the equipment to be installed in a data center with the resources available in the data center to efficiently allocate the equipment, with an emotion engine that recognizes user emotions. A specific embodiment of this system is described below.

[0829] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[0830] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[0831] Next, the server uses the acquired data to train a machine learning model (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[0832] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[0833] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[0834] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[0835] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's voice, facial expressions, and input content to identify the user's emotional state. The server analyzes the emotional data obtained from the emotion engine and adjusts the system's display interface and operation flow based on the results. For example, if the user is stressed, the system will either provide a simpler interface or enhance its assistance functions.

[0836] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[0837] Next, the emotion engine recognizes the user's emotional state. For example, if it detects that the user is feeling stressed during an interaction, the server simplifies the interface and adjusts it to allow the user to interact more smoothly. If the user is satisfied, the emotion engine also provides detailed resource allocation options, allowing the user to engage more deeply.

[0838] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation. The combination with the emotion engine improves the user experience and reduces stress and frustration.

[0839] The following describes the processing flow.

[0840] Step 1:

[0841] The user logs into the system. The user enters appropriate authentication information, such as a username and password, to obtain permission to access the system.

[0842] Step 2:

[0843] The server retrieves past installation growth data from the database. Specifically, it executes SQL queries to extract data in order to retrieve installation records for the past three years.

[0844] Step 3:

[0845] The server uses the acquired installation data to train a machine learning model (e.g., a linear regression model). This allows the model to learn past data patterns and prepare to predict future increases in installation numbers.

[0846] Step 4:

[0847] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[0848] Step 5:

[0849] The server generates a list of equipment to be installed in the next fiscal year based on predictions. Specifically, it creates a list that includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[0850] Step 6:

[0851] The server retrieves data center resource information (e.g., power capacity, cooling capacity, available space). It then issues queries to the facility management system to obtain the latest resource status.

[0852] Step 7:

[0853] The requirements for the equipment where the servers are planned to be installed are compared with the resources of the data center. The suitability is determined by evaluating whether the requirements for each piece of equipment can be met with the current resources of the data center.

[0854] Step 8:

[0855] The server allocates equipment to each data center. It selects data centers that maximize resource utilization efficiency and can accommodate the necessary equipment without excess or shortage. It then develops an allocation plan and places the equipment in the corresponding data centers.

[0856] Step 9:

[0857] The server saves the allocation results to the database. The allocation plan is saved to the database so that it can be referenced and modified later.

[0858] Step 10:

[0859] The emotion engine recognizes the user's emotional state. It analyzes the voice, facial expressions, and input content the user provides during operation to identify stress levels and satisfaction levels.

[0860] Step 11:

[0861] The server adjusts the system's display interface and operation flow based on data obtained from the emotion engine. For example, if the system detects that the user is stressed, it simplifies the interface and enhances assistance features.

[0862] Step 12:

[0863] The server uses the sentiment engine's results to inform the user of the allocation decision in the most optimal way. For example, when the user is satisfied, it provides detailed resource allocation options, allowing the user to be more deeply involved.

[0864] Step 13:

[0865] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[0866] In this way, the system utilizes an emotion engine to operate in accordance with the user's emotional state, achieving optimal resource management and efficient data center utilization.

[0867] (Example 2)

[0868] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0869] Ensuring consistency between the equipment planned for installation in the data center and the actual resources available, and efficiently allocating equipment, are crucial requirements. Furthermore, improving system usability and reducing user stress are also important challenges.

[0870] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0871] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for obtaining data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means including an emotion engine that recognizes user emotions, and means for analyzing emotion data obtained from the emotion engine and adjusting the system interface and operation flow. This enables efficient allocation of equipment, improved user operability, and reduced stress.

[0872] "Past installation increase data" refers to record data regarding equipment installed in data centers in the past and the increase in that number.

[0873] A "machine learning algorithm" is a computational method used to learn patterns and rules from data and perform predictions and classifications.

[0874] The "List of Equipment to be Installed" is information that shows a list of equipment that is planned to be installed in the data center in the next fiscal year.

[0875] "Data center resource information" refers to information about the resources necessary for installing equipment in a data center, such as power capacity, cooling capacity, and available space.

[0876] "Requirements for equipment to be installed" refers to the resource requirements, such as power, cooling, and space, that the equipment to be installed in the data center will need.

[0877] An "emotion engine" is a system that analyzes and identifies a user's emotional state based on their voice, facial expressions, input content, and other factors.

[0878] "Means for adjusting the interface and operation flow" refers to functions that change and optimize the system's display screen and operation procedures based on the user's emotional state.

[0879] "Allocation results" refer to information regarding the plan for efficiently placing equipment in each data center and the results thereof.

[0880] This invention provides a system that efficiently compares equipment to be installed in a data center with the resources of the data center and allocates the equipment optimally. Furthermore, it incorporates an emotion engine that recognizes user emotions to improve usability.

[0881] First, the user logs into the system. The user uses a browser or a dedicated application to enter appropriate authentication information (ID and password). The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the user can access the administration screen.

[0882] Next, the server collects historical installation increase data. This data is obtained from equipment installation records for the past several years stored in the database. An SQL query is executed to extract the data in a format such as "SELECT FROM installation_records WHERE year BETWEEN 2019 AND 2021;".

[0883] Based on the acquired data, the server trains a linear regression model using a machine learning library (e.g., Scikit-learn). This model is used to predict future increases in the number of installations. For example, if past installation data shows 20, 25, and 30, it can predict 35 for the following year.

[0884] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year. This equipment list is saved in JSON or CSV format and used for future management.

[0885] Next, the server retrieves resource information for the data center. This resource information includes power capacity, cooling capacity, and available space. The server issues a query to the facility management system and retrieves the data in a format such as "SELECT FROM resource WHERE datacenterID = 1;".

[0886] Based on the acquired resource information, the server compares the requirements of the planned equipment (power, cooling, space) with the resources of the data center. For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server will evaluate the resources of each data center.

[0887] Based on the comparison results, the servers allocate equipment to each data center. The allocation results are formulated as a specific deployment plan, such as "20 servers in Data Center 1 and 15 servers in Data Center 2." This plan is stored in a database and used for future implementation.

[0888] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The server invokes the emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input. Based on the resulting emotion data, it adjusts the interface and operation flow.

[0889] For example, if the server detects that a user is experiencing stress while operating the system, it can simplify the interface and streamline the operation. Furthermore, if the user is satisfied, it can provide more detailed resource allocation options.

[0890] As a result, this system achieves efficient allocation of equipment, improved user experience, and reduced stress.

[0891] A concrete example would be a user logging into the system and seeing records showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the system predicts that 35 servers will be needed in the next fiscal year. Next, it obtains resource information for each data center and decides to allocate 20 servers to data center 1 and 15 servers to data center 2.

[0892] Furthermore, the emotion engine detects when the user is experiencing stress during their interaction, and the server provides a simple interface. In this way, the system's usability and the user experience are optimized.

[0893] An example of a prompt message for a generating AI model is, "Generate a list of servers scheduled for installation in the next fiscal year and efficiently allocate them to each data center."

[0894] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0895] Step 1: User Login

[0896] Specific operation and input / output:

[0897] Users access the system using a browser or a dedicated application.

[0898] The user enters authentication information such as their ID and password.

[0899] Input: User authentication information (ID and password)

[0900] The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the server grants the user access to the administration screen.

[0901] Output: Authentication success / failure result and access rights to the administration screen

[0902] Step 2: Collecting past installation increase data

[0903] Specific operation and input / output:

[0904] The server executes SQL queries against the database to retrieve equipment installation records for the past several years.

[0905] Input: Installation records stored in the database

[0906] For example, execute a query like "SELECT FROM Installation Records WHERE Year BETWEEN 2019 AND 2021;".

[0907] Output: Past installation increase data

[0908] Step 3: Training and predicting machine learning models

[0909] Specific operation and input / output:

[0910] The server uses the collected data to train a linear regression model using a machine learning library (e.g., Scikit-learn).

[0911] Input: Past installation increase data

[0912] The server inputs new data into the trained model and predicts the increase in equipment installations for the following year.

[0913] Example: If past installation data shows 20, 25, and 30, then the forecast for the next year is 35.

[0914] Output: Predicted increase in the number of installations for the next fiscal year

[0915] Step 4: Generating the equipment list for the next fiscal year

[0916] Specific operation and input / output:

[0917] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year.

[0918] Input: Predicted increase in the number of installations for the next fiscal year

[0919] This device list is saved in JSON or CSV format.

[0920] Output: List of equipment scheduled for installation in the next fiscal year

[0921] Step 5: Obtain data center resource information

[0922] Specific operation and input / output:

[0923] The server issues a query to the data center's facility management system to retrieve resource information.

[0924] Input: Query to retrieve resource information

[0925] For example, execute the query "SELECT FROM resource WHERE datacenterID = 1;".

[0926] Output: Data center resource information (power capacity, cooling capacity, available space, etc.)

[0927] Step 6: Comparison of requirements and resources for the equipment to be installed.

[0928] Specific operation and input / output:

[0929] The server compares the requirements of each device with the resource information of the data center.

[0930] Input: Requirements for the equipment to be installed (power, cooling, space), data center resource information

[0931] For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the resource information is evaluated against those requirements.

[0932] Output: Resource evaluation results

[0933] Step 7: Develop an equipment allocation and placement plan.

[0934] Specific operation and input / output:

[0935] Based on the comparison results, the servers efficiently allocate equipment to each data center.

[0936] Input: Resource evaluation results

[0937] The allocation plan is then specified, for example, "20 units in Data Center 1, and 15 units in Data Center 2."

[0938] The generated deployment plan is saved in the database.

[0939] Output: Layout plan

[0940] Step 8: User emotion recognition by the emotion engine

[0941] Specific operation and input / output:

[0942] The server calls an emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input.

[0943] Input: User's voice, facial expressions, and input content

[0944] The server identifies the user's emotional state (e.g., stress, satisfaction) from the analysis results.

[0945] Output: Sentiment data

[0946] Step 9: Adjusting the Interface

[0947] Specific operation and input / output:

[0948] The server adjusts the interface and operation flow based on user sentiment data.

[0949] Input: Sentiment data

[0950] For example, if a user is experiencing stress, provide a simplified interface.

[0951] Output: Adjusted interface, operation flow

[0952] Step 10: Saving and notifying results

[0953] Specific operation and input / output:

[0954] The server saves the final allocation results and user actions to the database.

[0955] Input: Final allocation result, user actions

[0956] The server notifies the user's terminal that new information is available.

[0957] Output: Saved data, notification messages

[0958] (Application Example 2)

[0959] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0960] In data centers, expanding equipment and managing resources are crucial for efficient operation and optimal resource allocation. However, performing these tasks manually is complex and time-consuming, and can lead to operational errors and decreased efficiency, especially depending on the user's emotional state. Therefore, there is a need for a system that uses historical data for prediction, automated resource allocation, and adapts the user interface according to the user's emotional state.

[0961] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0962] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for recognizing the user's emotions, and means for adjusting the system's operating interface based on the user's emotions. This enables efficient and appropriate equipment allocation and flexible interface adjustment according to the user's emotional state.

[0963] "Installation increase data" refers to records of increases or decreases in the number of devices and equipment installed in the past.

[0964] A "machine learning algorithm" is a mathematical method that learns patterns from data and uses those patterns to make future predictions and classifications.

[0965] The "list of equipment to be installed" is a list of equipment and facilities that are planned to be installed in the future.

[0966] A "data center" is a facility that centrally houses a large number of computers and storage devices for data storage and processing.

[0967] "Resource information" refers to information regarding the utilization status of resources in a data center, such as power capacity, cooling capacity, and available space.

[0968] "Equipment requirements" refer to the conditions and specifications, such as power, cooling, and space, necessary for the operation of equipment or facilities.

[0969] "User emotions" refer to the psychological and physiological state and mood of the user operating the system.

[0970] An "operation interface" refers to the screens and input methods that users use to interact with and operate a system.

[0971] "Emotion recognition means" refers to technologies and devices that analyze a user's voice and facial expressions to identify their emotional state.

[0972] "Means for allocating equipment to appropriate data centers" refers to methods or algorithms for placing equipment in data centers that meet the requirements of the equipment to be installed.

[0973] "Means of adjusting the system's operating interface based on emotions" refers to methods and technologies for changing the operating screen or input method in consideration of the user's emotional state.

[0974] This invention is a system that improves the efficiency of equipment installation and user experience in data centers. The system collects historical installation growth data and uses machine learning algorithms to predict future installation growth. Based on the predicted growth, it creates a list of equipment to be installed and allocates equipment to appropriate data centers by comparing data center resource information with equipment requirements. Furthermore, it includes a function to recognize user emotions and adjust the operating interface based on those emotions.

[0975] 1. Hardware and software used

[0976] The system is implemented using the following hardware and software:

[0977] server:

[0978] Computational resources for data collection and machine learning.

[0979] Connect to the database and retrieve past installation increase data.

[0980] Perform calculations to formulate equipment allocation and placement plans.

[0981] camera:

[0982] A webcam that captures the user's facial image for emotion recognition.

[0983] DeepFace:

[0984] An emotion recognition library for analyzing user emotions.

[0985] scikit-learn:

[0986] A library for predicting future increases in installation numbers using machine learning algorithms (linear regression models).

[0987] Tkinter:

[0988] A GUI library for building user interfaces.

[0989] 2. System Processing Overview

[0990] The server first collects past installation increase data from a database and uses a machine learning algorithm to predict future installation increases based on this data. Based on the prediction results, it creates a list of equipment to be installed in the next year, obtains resource information (power capacity, cooling capacity, available space), and optimally allocates equipment to each data center.

[0991] When a user logs into the system, the camera captures the user's face, and the DeepFace library is used for emotion recognition. If the user is stressed, Tkinter is used to simplify the interface and improve ease of use.

[0992] 3. Specific examples

[0993] The user logs into the system, and based on data from the past three years, it predicts that 30 robots will be needed for the next year. The server retrieves resource information from the database and appropriately allocates 20 robots to data center 1 and 10 robots to data center 2 based on the required resources.

[0994] The system captures the user's face through the camera and recognizes that the user is experiencing stress. In this case, the system improves user experience by simplifying the interface and adjusting it to display only essential information.

[0995] Example of a prompt

[0996] "Using data showing that the number of robots deployed has increased from 20 to 25 to 30 over the past three years, predict the number of robots needed for the next year. Additionally, create a program that recognizes user emotions and simplifies the interface if the user is experiencing stress."

[0997] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0998] Program processing steps

[0999] Step 1:

[1000] The server collects historical installation growth data from the database. In this step, it queries the database to retrieve installation records for the past several years (e.g., the past three years). The input is the installation growth data from the database, and the output is a dataset that uses this data to be passed to the next step. Specifically, the server issues an SQL query to retrieve the historical installation growth data in list format.

[1001] Step 2:

[1002] The server uses a machine learning algorithm based on the collected data to predict future installation increases. In this step, a model is trained using a linear regression model from scikit-learn, for example, to predict the installation increase needed for the next year. The input is past installation increase data, and the output is the predicted installation increase. Specifically, the server fits the data to the model and calculates the installation increase for the next year.

[1003] Step 3:

[1004] The server creates a list of equipment to be installed based on the predicted increase in capacity. This step lists the equipment to be installed in the next fiscal year according to the predicted increase in capacity. The input is the predicted increase in capacity, and the output is the list of equipment to be installed. Specifically, the server generates a list detailing the equipment to be installed in the next fiscal year.

[1005] Step 4:

[1006] The server retrieves data center resource information (power capacity, cooling capacity, available space). In this step, it issues queries to the facility management system to obtain the latest resource status. The input is query information, and the output is data center resource information. Specifically, the server accesses the facility management system and retrieves resource information for each facility.

[1007] Step 5:

[1008] The server compares the requirements of the equipment to be installed with the resources of the data center and allocates the equipment to the appropriate data center. In this step, the requirements of each piece of equipment are matched with the resource information of the data center to verify that the resources are adequately met. The input is a list of the equipment to be installed and resource information, and the output is the equipment allocation result. Specifically, the server calculates the resources required for each piece of equipment and allocates them to the optimal data center.

[1009] Step 6:

[1010] The user logs into the system. In this step, the user enters appropriate authentication information and is granted access to the system. The input is the user's authentication information, and the output is a notification of successful or unsuccessful login to the system. Specifically, the terminal provides a login screen and sends the user's authentication information to the server.

[1011] Step 7:

[1012] The server captures the user's face image via the camera and performs emotion analysis using the DeepFace library to recognize the user's emotions. In this step, the user's emotions are identified based on the video captured by the camera. The input is the captured face image, and the output is the identified emotion data. Specifically, the terminal activates the camera and passes the acquired face image to the emotion recognition algorithm.

[1013] Step 8:

[1014] The server adjusts the system's user interface based on emotional data. In this step, the interface is simplified when the user is stressed and more detailed when they are satisfied. The input is emotional data, and the output is the adjusted user interface. Specifically, the server changes the interface layout and functionality according to the user's emotional state.

[1015] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1016] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1017] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1018] [Fourth Embodiment]

[1019] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1020] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1021] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1022] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1023] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1024] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1025] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1026] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1027] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1028] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1030] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1032] This invention relates to a system that compares equipment to be installed in a data center with the resources available in the data center, and efficiently allocates the equipment. A specific embodiment of this system is described below.

[1033] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[1034] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[1035] Next, the server uses the acquired data to train a machine learning algorithm (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[1036] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[1037] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[1038] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[1039] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[1040] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation.

[1041] The following describes the processing flow.

[1042] Step 1:

[1043] The user logs into the system. The user enters appropriate authentication information (such as username and password) and is granted access to the system.

[1044] Step 2:

[1045] The server retrieves past installation growth data from the database. Specifically, it executes an SQL query against the database to retrieve installation records for the past three years.

[1046] Step 3:

[1047] The server uses the acquired installation data to train a machine learning model. For example, a linear regression model can be used to learn past installation trends.

[1048] Step 4:

[1049] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[1050] Step 5:

[1051] The server generates a list of equipment to be installed in the next fiscal year based on predictions. This list includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[1052] Step 6:

[1053] The server retrieves resource information from the data center. It issues queries to the facility management system to obtain information such as power capacity, cooling capacity, and available space for each data center.

[1054] Step 7:

[1055] Compare the requirements of the equipment where the servers are planned to be installed with the resources of the data center. Evaluate whether the requirements of each piece of equipment can be met with the current resources of the data center.

[1056] Step 8:

[1057] The server allocates equipment to each data center. Considering resource utilization efficiency, an allocation plan is developed to place equipment in the most suitable data center.

[1058] Step 9:

[1059] The server saves the allocation results to the database. The allocation plan is saved so that it can be referenced and modified later.

[1060] Step 10:

[1061] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[1062] (Example 1)

[1063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1064] As the amount of equipment planned for installation in data centers increases, efficiently managing resources and appropriately allocating equipment without excess or shortage becomes challenging. In particular, there is a need for a means to accurately understand future expansion forecasts and data center resource information, and to make optimal allocations. Furthermore, it is crucial that the system is easily accessible to users and that the status can be checked from a management screen.

[1065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1066] In this invention, the server includes means for a user to enter authentication information and log in to the system; means for collecting past installation increase data; means for predicting future installation increases using a machine learning algorithm; means for creating a list of equipment to be installed based on the predicted increase; means for obtaining data center resource information; means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center; and means for saving the allocation results to a database and notifying the user of that information. This makes it possible to maximize resource utilization efficiency and realize a system that is highly convenient for users.

[1067] A "user" refers to an individual or organization that accesses and operates a system.

[1068] "Authentication information" refers to information used to identify a user and verify their access rights to the system, such as a user ID and password.

[1069] "Logging in" refers to the process of accessing and making available a system using authentication credentials.

[1070] A "server" refers to a computer system that performs tasks such as data processing and resource management.

[1071] "Installation increase data" refers to records of equipment newly installed in data centers in the past.

[1072] A "machine learning algorithm" refers to a statistical method used to analyze data and make predictions about future trends.

[1073] The "list of equipment to be installed" refers to a list of equipment that is scheduled to be installed in the future.

[1074] A "data center" refers to a facility where computers and other related equipment are installed.

[1075] "Resource information" refers to management information such as power capacity, cooling capacity, and available space within a data center.

[1076] "Equipment requirements" refer to the specific conditions such as power, cooling, and space required by the equipment to be installed.

[1077] "Comparison" refers to the process of matching the requirements of the equipment to be installed with the resource information of the data center and evaluating their suitability.

[1078] "Allocation" refers to the process of deciding where to place the equipment to be installed in the most appropriate data center.

[1079] A "database" refers to an information system that systematically manages large amounts of data and facilitates searching and updating.

[1080] "Notification" refers to the act of a system communicating information to a user.

[1081] A "facility management system" refers to a software system used to manage the status of resources and equipment within a data center.

[1082] A "resource allocation plan" refers to a detailed plan for efficiently using resources within a data center and arranging equipment accordingly.

[1083] This invention relates to a system for efficiently allocating equipment to be installed in a data center. This system enables users to optimize resource management with simple operations and formulate an appropriate equipment placement plan based on predictions.

[1084] First, the user logs into the system. The user enters appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen. The authentication process uses the user ID and password, which the server verifies against the database.

[1085] Next, the server collects past installation increase data. Specifically, the server issues queries to the database to extract past installation records. An example query is "SELECT FROM InstallationRecords WHERE Year >= 2019;". This data is temporarily stored in the server's memory.

[1086] After collecting historical data, the server uses a machine learning algorithm to predict future increases in the number of installations. The server builds and trains a linear regression model using machine learning libraries such as scikit-learn. The server uses the trained model to make predictions and generates a list of planned installations for the next year based on the results.

[1087] Next, the server retrieves resource information from the data center. The server issues a query to the facility management system to obtain the latest resource status. An example query is "SELECT FROM ResourceStatus;". This resource information is also temporarily stored in the server's memory.

[1088] The server matches the requirements of the equipment to be installed with the data center's resource information. It extracts the requirements for each piece of equipment (e.g., power, cooling, space) and compares them with the retrieved resource information. This verifies that resources are adequately met and helps develop an efficient resource allocation plan.

[1089] As a concrete example, based on records showing an increase of 20, 25, and 30 servers over the past three years, we predict that 35 servers will be needed in the next fiscal year. Subsequently, we obtain resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks). If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, we decide to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[1090] Finally, the server saves the allocation results to the database. The server then notifies the user of this information, and the user can check the allocation results through the system's administration screen. This enables optimal resource management and efficient operation.

[1091] An example of a prompt message is: "Train a linear regression model using installation data from the past three years to predict next year's server installation plan. Also, obtain the latest resource information for the data center and develop a deployment plan to optimally allocate equipment."

[1092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1093] Step 1:

[1094] The user logs into the system.

[1095] The user accesses the system and enters authentication information (e.g., user ID and password). The server verifies this entered authentication information against the database. If authentication is successful, the server starts a session for the user and grants access to the administration screen. The input is the user ID and password, and the output is the authentication session.

[1096] Step 2:

[1097] The server collects past installation increase data.

[1098] The server issues an SQL query to the database to extract past installation records. Specifically, it executes the query "SELECT FROM InstallationRecords WHERE Year >= 2019;". The server temporarily stores the retrieved data in memory. The input is a query for installation increase data, and the output is past installation record data.

[1099] Step 3:

[1100] The server uses a machine learning algorithm to predict future increases in installation numbers.

[1101] The server loads machine learning libraries such as scikit-learn and builds a linear regression model using historical installation data. Next, it trains the model to predict future installation increases. The input is historical installation records, and the output is the predicted installation increase for the next year.

[1102] Step 4:

[1103] The server creates a list of equipment scheduled for installation in the next fiscal year.

[1104] The server creates a list of planned equipment installations for the next fiscal year based on the predicted increase in installations. This generates a list of specific equipment to be installed. The input is the predicted increase in installations, and the output is the list of planned equipment installations for the next fiscal year.

[1105] Step 5:

[1106] The server retrieves resource information from the data center.

[1107] The server issues an SQL query to the equipment management system to retrieve the latest resource information. Specifically, it executes the query "SELECT FROM ResourceStatus;". The server temporarily stores this information in memory. The input is the query for resource information, and the output is the latest resource information data.

[1108] Step 6:

[1109] Compare the requirements of the equipment where the server will be installed with the resources of the data center.

[1110] The server loads a list of planned equipment and resource information, and compares the requirements (e.g., power, cooling, space) and resources for each. This verifies that the resources are adequately met. The input is the list of planned equipment and resource information, and the output is a resource allocation plan.

[1111] Step 7:

[1112] The server allocates the equipment to the appropriate data center.

[1113] Based on the comparison results, the server allocates the equipment to be installed in each data center. This ensures optimal resource utilization. The server saves the allocation results to a database and formulates a deployment plan. The input is the resource allocation plan, and the output is the allocation results and the deployment plan.

[1114] Step 8:

[1115] The server notifies the user of the allocation result.

[1116] The server notifies the user of the allocation results, making them available for viewing from the system's administration screen. This allows users to achieve optimal resource management. The input is the allocation results, and the output is the notification to the user.

[1117] (Application Example 1)

[1118] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1119] There is a need to simultaneously address two different challenges: efficiently managing data center resources and optimizing parking locations for autonomous vehicles. This requires streamlining complex tasks such as data center equipment installation planning, vehicle resource management, and parking location selection, thereby reducing costs and improving operational efficiency.

[1120] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1121] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for collecting vehicle sensor data and evaluating parking spaces, and means for comparing vehicle resources with the conditions of the parking space and selecting the optimal parking location. This enables efficient management of data center resources and optimization of parking location selection for autonomous vehicles.

[1122] "Installation increase data" refers to data on the historical increase in the number of equipment installations in data centers and other related facilities.

[1123] A "machine learning algorithm" is a mathematical method that learns patterns from past data to make predictions and decisions about the future.

[1124] The "List of Equipment to be Installed" is a list of equipment that is planned to be installed in the data center in the future, based on the predicted increase in installations.

[1125] "Data center resource information" refers to information about the current state of resources available to the data center, such as power capacity, cooling capacity, and available space.

[1126] "Equipment requirements" refer to the conditions such as power, cooling, and space necessary for the equipment to be installed to operate normally.

[1127] "Sensor data" refers to information such as battery level, internal temperature, and available space collected by sensors installed in autonomous vehicles.

[1128] "Parking space evaluation" is the process of using the vehicle's cameras and sensors to determine how available or suitable a parking space is at present.

[1129] An "optimal parking spot" is the most suitable parking location for a vehicle, based on its resource information and the conditions of the parking space.

[1130] This invention provides a system that integrates data center resource management and optimization of parking locations for autonomous vehicles. This system includes the following means:

[1131] First, the server collects historical installation growth data. This data is obtained from installation records stored in a database for the past several years. The server queries the database to extract historical installation records.

[1132] Next, the server uses the acquired data to train a machine learning algorithm. For example, it uses a linear regression model to predict future increases in the number of installations. Based on the prediction results, it generates a list of equipment scheduled for installation in the following year.

[1133] The server also retrieves resource information from the data center. This resource information is obtained from the data center's facility management system. Queries are issued to the facility management system to retrieve the latest resource status.

[1134] Next, the server compares the requirements of the equipment to be installed (e.g., power consumption, cooling requirements, installation space) with the resources of the data center to ensure that the resources are adequately met. Then, it allocates the equipment to the appropriate data center.

[1135] Furthermore, the server collects data from the vehicle's sensors, including battery level, internal temperature, and available space. It also uses data from the vehicle's cameras and sensors to assess the availability of parking spaces.

[1136] The server uses the collected data to compare the vehicle's resources with the conditions of the parking space and select the optimal parking location. A linear regression model is applied to this process to predict the most suitable parking location for the vehicle.

[1137] The hardware used includes cameras, temperature sensors, space sensors, and servers mounted on the autonomous vehicle. The software used includes OpenCV for data processing, NumPy for data analysis, and scikit-learn for machine learning models.

[1138] As a concrete example, real-time data is collected from in-vehicle cameras and sensors, and this data is processed using OpenCV. For instance, to evaluate the availability of parking spaces, camera data is binarized and the number of white pixels is counted. Based on sensor data (battery level, internal temperature, available space), basic conditions are evaluated, and the optimal parking location is selected using a linear regression model.

[1139] An example of a prompt message is: "Analyze the availability of parking spaces and recommend the best parking spot considering the vehicle's battery level, interior temperature, and available space."

[1140] This will enable more efficient resource management in data centers and optimize the selection of parking locations for autonomous vehicles.

[1141] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1142] Step 1:

[1143] The server collects historical installation data from the database. First, it issues a query to the database to extract past installation records. This data includes the quantity of equipment installed over the past few years, the installation date and time, and the installation location. Using the configured query as input, the server obtains historical installation data as output.

[1144] Step 2:

[1145] The server trains a machine learning algorithm using collected installation increase data. It applies a linear regression model to learn trends for predicting future installation increases. Historical installation data is used as input, and the optimal regression model is output through computation.

[1146] Step 3:

[1147] The server creates a list of equipment to be installed based on the predicted increase in capacity. Based on the prediction results, it generates a list of equipment expected to be installed in the next fiscal year. Machine learning prediction results are used as input, and a list of equipment to be installed is generated as output.

[1148] Step 4:

[1149] The server retrieves data center resource information. This is done by querying the facility management system to obtain the latest information on power capacity, cooling capacity, and available space. A query is set as the input, and data center resource information is obtained as the output.

[1150] Step 5:

[1151] The server compares the requirements of the equipment to be installed (power consumption, cooling requirements, installation space) with the resource information of the data center. It checks whether each piece of equipment meets the requirements and allocates the equipment to the appropriate data center. The equipment requirements and data center resource information are used as input, and the output is the allocation result of the optimal installation location.

[1152] Step 6:

[1153] The server collects sensor data (battery level, internal temperature, available space) from the autonomous vehicle. It acquires real-time data from each sensor and takes the sensor data as input. Status information for each sensor is obtained as output.

[1154] Step 7:

[1155] The server evaluates the availability of parking spaces based on data from the vehicle's cameras and sensors. It uses OpenCV to process camera data and evaluate available spaces. Camera data is used as input, and the evaluation result for available spaces is obtained as output.

[1156] Step 8:

[1157] The server compares vehicle resources and parking space conditions based on collected data to select the optimal parking location. A linear regression model is used to calculate a parking location evaluation score. Sensor data and the evaluation results of available spaces are used as input, and the output is the selection result of the optimal parking location.

[1158] Step 9:

[1159] The server saves the allocation results and parking location selection results to a database and notifies the user of this information. It records the allocation results and optimal parking location information in the database and notifies the user. The allocation results and selection results are used as input, and the user notification is output.

[1160] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1161] This invention combines a system that compares the equipment to be installed in a data center with the resources available in the data center to efficiently allocate the equipment, with an emotion engine that recognizes user emotions. A specific embodiment of this system is described below.

[1162] First, the user logs into the system. The user enters the appropriate authentication information and is granted access to the system. After logging in, the user can access the system's administration screen.

[1163] The server collects historical data on equipment installation increases. This data is obtained from installation records stored in a database over the past few years. Queries are executed against the database to extract historical installation records.

[1164] Next, the server uses the acquired data to train a machine learning model (for example, a linear regression model). This allows the server to predict future increases in the number of installations. Based on the prediction results, the server generates a list of equipment to be installed in the following year.

[1165] The server retrieves resource information from the data center (power capacity, cooling capacity, available space). This resource information is obtained from the data center's facility management system. The server issues queries to the facility management system to retrieve the latest resource status.

[1166] Next, the server compares the requirements of the equipment to be installed (e.g., power, cooling, space) with the resources of the data center. It matches the requirements of each piece of equipment with the data center's resource information to verify that the resources are adequately met.

[1167] Based on the comparison results, the server allocates equipment to each data center. The data center is selected to maximize resource utilization efficiency and ensure the equipment can be installed without excess or deficiency. Based on the allocation results, an equipment placement plan is formulated.

[1168] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's voice, facial expressions, and input content to identify the user's emotional state. The server analyzes the emotional data obtained from the emotion engine and adjusts the system's display interface and operation flow based on the results. For example, if the user is stressed, the system will either provide a simpler interface or enhance its assistance functions.

[1169] As a concrete example, a user logs into the system and checks installation data for the past three years. For instance, records are obtained showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the server predicts that 35 servers will be needed in the next year. A list of 35 servers to be installed in the next year is generated, and resource information for each data center is obtained. Resource information for Data Center 1 (power capacity 200kW, cooling capacity 500kW, 50 available racks) and Data Center 2 (power capacity 150kW, cooling capacity 400kW, 40 available racks) is checked. If each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server decides to allocate 20 servers to Data Center 1 and 15 servers to Data Center 2.

[1170] Next, the emotion engine recognizes the user's emotional state. For example, if it detects that the user is feeling stressed during an interaction, the server simplifies the interface and adjusts it to allow the user to interact more smoothly. If the user is satisfied, the emotion engine also provides detailed resource allocation options, allowing the user to engage more deeply.

[1171] The server saves the allocation results to a database and notifies the user of this information. This allows the user to achieve optimal resource management and efficient operation. The combination with the emotion engine improves the user experience and reduces stress and frustration.

[1172] The following describes the processing flow.

[1173] Step 1:

[1174] The user logs into the system. The user enters appropriate authentication information, such as a username and password, to obtain permission to access the system.

[1175] Step 2:

[1176] The server retrieves past installation growth data from the database. Specifically, it executes SQL queries to extract data in order to retrieve installation records for the past three years.

[1177] Step 3:

[1178] The server uses the acquired installation data to train a machine learning model (e.g., a linear regression model). This allows the model to learn past data patterns and prepare to predict future increases in installation numbers.

[1179] Step 4:

[1180] The server uses a trained machine learning model to predict the increase in installations for the next fiscal year. The prediction result yields the number of servers needed for the next fiscal year.

[1181] Step 5:

[1182] The server generates a list of equipment to be installed in the next fiscal year based on predictions. Specifically, it creates a list that includes detailed information about each piece of equipment (such as required power, cooling capacity, and space requirements).

[1183] Step 6:

[1184] The server retrieves data center resource information (e.g., power capacity, cooling capacity, available space). It then issues queries to the facility management system to obtain the latest resource status.

[1185] Step 7:

[1186] The requirements for the equipment where the servers are planned to be installed are compared with the resources of the data center. The suitability is determined by evaluating whether the requirements for each piece of equipment can be met with the current resources of the data center.

[1187] Step 8:

[1188] The server allocates equipment to each data center. It selects data centers that maximize resource utilization efficiency and can accommodate the necessary equipment without excess or shortage. It then develops an allocation plan and places the equipment in the corresponding data centers.

[1189] Step 9:

[1190] The server saves the allocation results to the database. The allocation plan is saved to the database so that it can be referenced and modified later.

[1191] Step 10:

[1192] The emotion engine recognizes the user's emotional state. It analyzes the voice, facial expressions, and input content the user provides during operation to identify stress levels and satisfaction levels.

[1193] Step 11:

[1194] The server adjusts the system's display interface and operation flow based on data obtained from the emotion engine. For example, if the system detects that the user is stressed, it simplifies the interface and enhances assistance features.

[1195] Step 12:

[1196] The server uses the sentiment engine's results to inform the user of the allocation decision in the most optimal way. For example, when the user is satisfied, it provides detailed resource allocation options, allowing the user to be more deeply involved.

[1197] Step 13:

[1198] The server notifies the user of the allocation result. The user is notified of the allocation result via email or system notification.

[1199] In this way, the system utilizes an emotion engine to operate in accordance with the user's emotional state, achieving optimal resource management and efficient data center utilization.

[1200] (Example 2)

[1201] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1202] Ensuring consistency between the equipment planned for installation in the data center and the actual resources available, and efficiently allocating equipment, are crucial requirements. Furthermore, improving system usability and reducing user stress are also important challenges.

[1203] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1204] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for obtaining data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means including an emotion engine that recognizes user emotions, and means for analyzing emotion data obtained from the emotion engine and adjusting the system interface and operation flow. This enables efficient allocation of equipment, improved user operability, and reduced stress.

[1205] "Past installation increase data" refers to record data regarding equipment installed in data centers in the past and the increase in that number.

[1206] A "machine learning algorithm" is a computational method used to learn patterns and rules from data and perform predictions and classifications.

[1207] The "List of Equipment to be Installed" is information that shows a list of equipment that is planned to be installed in the data center in the next fiscal year.

[1208] "Data center resource information" refers to information about the resources necessary for installing equipment in a data center, such as power capacity, cooling capacity, and available space.

[1209] "Requirements for equipment to be installed" refers to the resource requirements, such as power, cooling, and space, that the equipment to be installed in the data center will need.

[1210] An "emotion engine" is a system that analyzes and identifies a user's emotional state based on their voice, facial expressions, input content, and other factors.

[1211] "Means for adjusting the interface and operation flow" refers to functions that change and optimize the system's display screen and operation procedures based on the user's emotional state.

[1212] "Allocation results" refer to information regarding the plan for efficiently placing equipment in each data center and the results thereof.

[1213] This invention provides a system that efficiently compares equipment to be installed in a data center with the resources of the data center and allocates the equipment optimally. Furthermore, it incorporates an emotion engine that recognizes user emotions to improve usability.

[1214] First, the user logs into the system. The user uses a browser or a dedicated application to enter appropriate authentication information (ID and password). The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the user can access the administration screen.

[1215] Next, the server collects historical installation increase data. This data is obtained from equipment installation records for the past several years stored in the database. An SQL query is executed to extract the data in a format such as "SELECT FROM installation_records WHERE year BETWEEN 2019 AND 2021;".

[1216] Based on the acquired data, the server trains a linear regression model using a machine learning library (e.g., Scikit-learn). This model is used to predict future increases in the number of installations. For example, if past installation data shows 20, 25, and 30, it can predict 35 for the following year.

[1217] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year. This equipment list is saved in JSON or CSV format and used for future management.

[1218] Next, the server retrieves resource information for the data center. This resource information includes power capacity, cooling capacity, and available space. The server issues a query to the facility management system and retrieves the data in a format such as "SELECT FROM resource WHERE datacenterID = 1;".

[1219] Based on the acquired resource information, the server compares the requirements of the planned equipment (power, cooling, space) with the resources of the data center. For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the server will evaluate the resources of each data center.

[1220] Based on the comparison results, the servers allocate equipment to each data center. The allocation results are formulated as a specific deployment plan, such as "20 servers in Data Center 1 and 15 servers in Data Center 2." This plan is stored in a database and used for future implementation.

[1221] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The server invokes the emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input. Based on the resulting emotion data, it adjusts the interface and operation flow.

[1222] For example, if the server detects that a user is experiencing stress while operating the system, it can simplify the interface and streamline the operation. Furthermore, if the user is satisfied, it can provide more detailed resource allocation options.

[1223] As a result, this system achieves efficient allocation of equipment, improved user experience, and reduced stress.

[1224] A concrete example would be a user logging into the system and seeing records showing an increase of 20, 25, and 30 servers over the past three years. Based on this data, the system predicts that 35 servers will be needed in the next fiscal year. Next, it obtains resource information for each data center and decides to allocate 20 servers to data center 1 and 15 servers to data center 2.

[1225] Furthermore, the emotion engine detects when the user is experiencing stress during their interaction, and the server provides a simple interface. In this way, the system's usability and the user experience are optimized.

[1226] An example of a prompt message for a generating AI model is, "Generate a list of servers scheduled for installation in the next fiscal year and efficiently allocate them to each data center."

[1227] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1228] Step 1: User Login

[1229] Specific operation and input / output:

[1230] Users access the system using a browser or a dedicated application.

[1231] The user enters authentication information such as their ID and password.

[1232] Input: User authentication information (ID and password)

[1233] The server verifies the entered authentication information against the user information in the database and performs authentication. If authentication is successful, the server grants the user access to the administration screen.

[1234] Output: Authentication success / failure result and access rights to the administration screen

[1235] Step 2: Collecting past installation increase data

[1236] Specific operation and input / output:

[1237] The server executes SQL queries against the database to retrieve equipment installation records for the past several years.

[1238] Input: Installation records stored in the database

[1239] For example, execute a query like "SELECT FROM Installation Records WHERE Year BETWEEN 2019 AND 2021;".

[1240] Output: Past installation increase data

[1241] Step 3: Training and predicting machine learning models

[1242] Specific operation and input / output:

[1243] The server uses the collected data to train a linear regression model using a machine learning library (e.g., Scikit-learn).

[1244] Input: Past installation increase data

[1245] The server inputs new data into the trained model and predicts the increase in equipment installations for the following year.

[1246] Example: If past installation data shows 20, 25, and 30, then the forecast for the next year is 35.

[1247] Output: Predicted increase in the number of installations for the next fiscal year

[1248] Step 4: Generating the equipment list for the next fiscal year

[1249] Specific operation and input / output:

[1250] Based on the prediction results, the server generates a list of equipment to be installed in the next fiscal year.

[1251] Input: Predicted increase in the number of installations for the next fiscal year

[1252] This device list is saved in JSON or CSV format.

[1253] Output: List of equipment scheduled for installation in the next fiscal year

[1254] Step 5: Obtain data center resource information

[1255] Specific operation and input / output:

[1256] The server issues a query to the data center's facility management system to retrieve resource information.

[1257] Input: Query to retrieve resource information

[1258] For example, execute the query "SELECT FROM resource WHERE datacenterID = 1;".

[1259] Output: Data center resource information (power capacity, cooling capacity, available space, etc.)

[1260] Step 6: Comparison of requirements and resources for the equipment to be installed.

[1261] Specific operation and input / output:

[1262] The server compares the requirements of each device with the resource information of the data center.

[1263] Input: Requirements for the equipment to be installed (power, cooling, space), data center resource information

[1264] For example, if each server requires 5kW of power, 10kW of cooling, and 1 rack of space, the resource information is evaluated against those requirements.

[1265] Output: Resource evaluation results

[1266] Step 7: Develop an equipment allocation and placement plan.

[1267] Specific operation and input / output:

[1268] Based on the comparison results, the servers efficiently allocate equipment to each data center.

[1269] Input: Resource evaluation results

[1270] The allocation plan is then specified, for example, "20 units in Data Center 1, and 15 units in Data Center 2."

[1271] The generated deployment plan is saved in the database.

[1272] Output: Layout plan

[1273] Step 8: User emotion recognition by the emotion engine

[1274] Specific operation and input / output:

[1275] The server calls an emotion engine (e.g., EmotionAPI) to analyze the user's voice, facial expressions, and input.

[1276] Input: User's voice, facial expressions, and input content

[1277] The server identifies the user's emotional state (e.g., stress, satisfaction) from the analysis results.

[1278] Output: Sentiment data

[1279] Step 9: Adjusting the Interface

[1280] Specific operation and input / output:

[1281] The server adjusts the interface and operation flow based on user sentiment data.

[1282] Input: Sentiment data

[1283] For example, if a user is experiencing stress, provide a simplified interface.

[1284] Output: Adjusted interface, operation flow

[1285] Step 10: Saving and notifying results

[1286] Specific operation and input / output:

[1287] The server saves the final allocation results and user actions to the database.

[1288] Input: Final allocation result, user actions

[1289] The server notifies the user's terminal that new information is available.

[1290] Output: Saved data, notification messages

[1291] (Application Example 2)

[1292] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1293] In data centers, expanding equipment and managing resources are crucial for efficient operation and optimal resource allocation. However, performing these tasks manually is complex and time-consuming, and can lead to operational errors and decreased efficiency, especially depending on the user's emotional state. Therefore, there is a need for a system that uses historical data for prediction, automated resource allocation, and adapts the user interface according to the user's emotional state.

[1294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1295] In this invention, the server includes means for collecting past installation increase data, means for predicting future installation increases using a machine learning algorithm, means for creating a list of equipment to be installed based on the predicted increase, means for acquiring data center resource information, means for comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to an appropriate data center, means for recognizing the user's emotions, and means for adjusting the system's operating interface based on the user's emotions. This enables efficient and appropriate equipment allocation and flexible interface adjustment according to the user's emotional state.

[1296] "Installation increase data" refers to records of increases or decreases in the number of devices and equipment installed in the past.

[1297] A "machine learning algorithm" is a mathematical method that learns patterns from data and uses those patterns to make future predictions and classifications.

[1298] The "list of equipment to be installed" is a list of equipment and facilities that are planned to be installed in the future.

[1299] A "data center" is a facility that centrally houses a large number of computers and storage devices for data storage and processing.

[1300] "Resource information" refers to information regarding the utilization status of resources in a data center, such as power capacity, cooling capacity, and available space.

[1301] "Equipment requirements" refer to the conditions and specifications, such as power, cooling, and space, necessary for the operation of equipment or facilities.

[1302] "User emotions" refer to the psychological and physiological state and mood of the user operating the system.

[1303] An "operation interface" refers to the screens and input methods that users use to interact with and operate a system.

[1304] "Emotion recognition means" refers to technologies and devices that analyze a user's voice and facial expressions to identify their emotional state.

[1305] "Means for allocating equipment to appropriate data centers" refers to methods or algorithms for placing equipment in data centers that meet the requirements of the equipment to be installed.

[1306] "Means of adjusting the system's operating interface based on emotions" refers to methods and technologies for changing the operating screen or input method in consideration of the user's emotional state.

[1307] This invention is a system that improves the efficiency of equipment installation and user experience in data centers. The system collects historical installation growth data and uses machine learning algorithms to predict future installation growth. Based on the predicted growth, it creates a list of equipment to be installed and allocates equipment to appropriate data centers by comparing data center resource information with equipment requirements. Furthermore, it includes a function to recognize user emotions and adjust the operating interface based on those emotions.

[1308] 1. Hardware and software used

[1309] The system is implemented using the following hardware and software:

[1310] server:

[1311] Computational resources for data collection and machine learning.

[1312] Connect to the database and retrieve past installation increase data.

[1313] Perform calculations to formulate equipment allocation and placement plans.

[1314] camera:

[1315] A webcam that captures the user's facial image for emotion recognition.

[1316] DeepFace:

[1317] An emotion recognition library for analyzing user emotions.

[1318] scikit-learn:

[1319] A library for predicting future increases in installation numbers using machine learning algorithms (linear regression models).

[1320] Tkinter:

[1321] A GUI library for building user interfaces.

[1322] 2. System Processing Overview

[1323] The server first collects past installation increase data from a database and uses a machine learning algorithm to predict future installation increases based on this data. Based on the prediction results, it creates a list of equipment to be installed in the next year, obtains resource information (power capacity, cooling capacity, available space), and optimally allocates equipment to each data center.

[1324] When a user logs into the system, the camera captures the user's face, and the DeepFace library is used for emotion recognition. If the user is stressed, Tkinter is used to simplify the interface and improve ease of use.

[1325] 3. Specific examples

[1326] The user logs into the system, and based on data from the past three years, it predicts that 30 robots will be needed for the next year. The server retrieves resource information from the database and appropriately allocates 20 robots to data center 1 and 10 robots to data center 2 based on the required resources.

[1327] The system captures the user's face through the camera and recognizes that the user is experiencing stress. In this case, the system improves user experience by simplifying the interface and adjusting it to display only essential information.

[1328] Example of a prompt

[1329] "Using data showing that the number of robots deployed has increased from 20 to 25 to 30 over the past three years, predict the number of robots needed for the next year. Additionally, create a program that recognizes user emotions and simplifies the interface if the user is experiencing stress."

[1330] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1331] Program processing steps

[1332] Step 1:

[1333] The server collects historical installation growth data from the database. In this step, it queries the database to retrieve installation records for the past several years (e.g., the past three years). The input is the installation growth data from the database, and the output is a dataset that uses this data to be passed to the next step. Specifically, the server issues an SQL query to retrieve the historical installation growth data in list format.

[1334] Step 2:

[1335] The server uses a machine learning algorithm based on the collected data to predict future installation increases. In this step, a model is trained using a linear regression model from scikit-learn, for example, to predict the installation increase needed for the next year. The input is past installation increase data, and the output is the predicted installation increase. Specifically, the server fits the data to the model and calculates the installation increase for the next year.

[1336] Step 3:

[1337] The server creates a list of equipment to be installed based on the predicted increase in capacity. This step lists the equipment to be installed in the next fiscal year according to the predicted increase in capacity. The input is the predicted increase in capacity, and the output is the list of equipment to be installed. Specifically, the server generates a list detailing the equipment to be installed in the next fiscal year.

[1338] Step 4:

[1339] The server retrieves data center resource information (power capacity, cooling capacity, available space). In this step, it issues queries to the facility management system to obtain the latest resource status. The input is query information, and the output is data center resource information. Specifically, the server accesses the facility management system and retrieves resource information for each facility.

[1340] Step 5:

[1341] The server compares the requirements of the equipment to be installed with the resources of the data center and allocates the equipment to the appropriate data center. In this step, the requirements of each piece of equipment are matched with the resource information of the data center to verify that the resources are adequately met. The input is a list of the equipment to be installed and resource information, and the output is the equipment allocation result. Specifically, the server calculates the resources required for each piece of equipment and allocates them to the optimal data center.

[1342] Step 6:

[1343] The user logs into the system. In this step, the user enters appropriate authentication information and is granted access to the system. The input is the user's authentication information, and the output is a notification of successful or unsuccessful login to the system. Specifically, the terminal provides a login screen and sends the user's authentication information to the server.

[1344] Step 7:

[1345] The server captures the user's face image via the camera and performs emotion analysis using the DeepFace library to recognize the user's emotions. In this step, the user's emotions are identified based on the video captured by the camera. The input is the captured face image, and the output is the identified emotion data. Specifically, the terminal activates the camera and passes the acquired face image to the emotion recognition algorithm.

[1346] Step 8:

[1347] The server adjusts the system's user interface based on emotional data. In this step, the interface is simplified when the user is stressed and more detailed when they are satisfied. The input is emotional data, and the output is the adjusted user interface. Specifically, the server changes the interface layout and functionality according to the user's emotional state.

[1348] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1349] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1350] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1351] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1352] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1353] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1354] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1355] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1356] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1357] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1358] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1359] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1360] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1361] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1362] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1363] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1364] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1365] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1366] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1367] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1368] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1369] The following is further disclosed regarding the embodiments described above.

[1370] (Claim 1)

[1371] A means of collecting past installation increase data,

[1372] A method for predicting future increases in the number of installations using machine learning algorithms,

[1373] A means for creating a list of equipment to be installed based on the predicted increase,

[1374] A means of obtaining data center resource information,

[1375] A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center,

[1376] A system that includes this.

[1377] (Claim 2)

[1378] The system according to claim 1, which performs machine learning based on acquired installation increase data.

[1379] (Claim 3)

[1380] The system according to claim 1, which saves the allocation results in a database and notifies the user of that information.

[1381] "Example 1"

[1382] (Claim 1)

[1383] A means for users to enter authentication information and log in to the system,

[1384] A means of collecting past installation increase data,

[1385] A method for predicting future increases in the number of installations using machine learning algorithms,

[1386] A means for creating a list of equipment to be installed based on the predicted increase,

[1387] A means of obtaining data center resource information,

[1388] A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center,

[1389] A means of saving the allocation results to a database and notifying the user of that information,

[1390] A system that includes this.

[1391] (Claim 2)

[1392] The system according to claim 1, which performs machine learning based on acquired installation increase data.

[1393] (Claim 3)

[1394] The system according to claim 1, which formulates a resource allocation plan using resource information obtained from an equipment management system.

[1395] "Application Example 1"

[1396] (Claim 1)

[1397] A means of collecting past installation increase data,

[1398] A method for predicting future increases in the number of installations using machine learning algorithms,

[1399] A means for creating a list of equipment to be installed based on the predicted increase,

[1400] A means of obtaining data center resource information,

[1401] A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center,

[1402] A means of collecting vehicle sensor data and evaluating parking spaces,

[1403] A method for selecting the optimal parking location by comparing vehicle resources and parking space conditions,

[1404] A system that includes this.

[1405] (Claim 2)

[1406] The system according to claim 1, which performs machine learning based on acquired installation increase data and vehicle sensor data.

[1407] (Claim 3)

[1408] The system according to claim 1, which stores the allocation results and the selection results of parking spaces in a database and notifies the user of that information.

[1409] "Example 2 of combining an emotion engine"

[1410] (Claim 1)

[1411] A means of collecting past installation increase data,

[1412] A method for predicting future increases in the number of installations using machine learning algorithms,

[1413] A means for creating a list of equipment to be installed based on the predicted increase,

[1414] A means of obtaining data center resource information,

[1415] A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center,

[1416] A means including an emotion engine that recognizes the user's emotions,

[1417] A means of analyzing emotional data obtained from an emotion engine and adjusting the system interface and operation flow,

[1418] A system that includes this.

[1419] (Claim 2)

[1420] The system according to claim 1, which performs machine learning based on acquired installation increase data.

[1421] (Claim 3)

[1422] The system according to claim 1, which saves the allocation results in a database and notifies the user of that information.

[1423] "Application example 2 of combining emotional engines"

[1424] (Claim 1)

[1425] A means of collecting past installation increase data,

[1426] A method for predicting future increases in the number of installations using machine learning algorithms,

[1427] A means for creating a list of equipment to be installed based on the predicted increase,

[1428] A means of obtaining data center resource information,

[1429] A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center,

[1430] Means of recognizing user emotions,

[1431] A means of adjusting the system's operating interface based on user emotions,

[1432] A system that includes this.

[1433] (Claim 2)

[1434] The system according to claim 1, which performs machine learning based on acquired installation increase data.

[1435] (Claim 3)

[1436] The system according to claim 1, which saves the allocation results in a database and notifies the user of that information.

[1437] (Claim 4)

[1438] The system according to claim 1, further comprising means for simplifying or detailing the operating interface in accordance with the user's emotional state.

[1439] (Claim 5)

[1440] The system according to claim 1, further comprising means for capturing a user's facial image and identifying the user's emotions using an emotion recognition algorithm. [Explanation of Symbols]

[1441] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past installation increase data, A method for predicting future increases in the number of installations using machine learning algorithms, A means for creating a list of equipment to be installed based on the predicted increase, A means of obtaining data center resource information, A means of comparing the requirements of the equipment to be installed with the resources of the data center and allocating the equipment to the appropriate data center, A system that includes this.

2. The system according to claim 1, which performs machine learning based on acquired installation increase data.

3. The system according to claim 1, wherein the allocation results are stored in a database and the information is notified to the user.

Images