ウェブファーマー Product Lineup

In the transportation industry, route optimization faces many challenges, including rising fuel costs, a shortage of drivers, and demands from customers for shorter delivery times. Selecting the optimal route is essential for cost reduction and improving customer satisfaction in response to these challenges. The SLM/LLM emphasis system contributes to solving these issues. 【Use Cases】 - Optimization of delivery routes - Proposal of detour routes in emergencies - Response to real-time traffic conditions 【Effects of Implementation】 - Reduction in fuel costs - Shortening of delivery times - Improvement in customer satisfaction

• Other information systems

In the marketing industry, measuring and improving the effectiveness of advertisements is always required. In particular, rapid data analysis and flexible advertising strategies are essential to respond to the diversifying advertising media and the complexity of customer behavior. However, traditional AI often struggles to reflect specialized knowledge and industry-specific expressions, making effective ad management difficult. Our SLM/LLM emphasis system supports the maximization of advertising effectiveness. 【Use Cases】 - Measurement and analysis of advertising effectiveness - Generation of advertising creatives - Optimization of targeting 【Benefits of Implementation】 - Increased efficiency in ad management - Improved cost-effectiveness - Enhanced customer engagement

• Other information systems

In recruitment activities, the efficiency of document screening and interview evaluation is an important issue for the human resources department. Particularly, as the number and diversity of applicants increase, the time and effort required to identify suitable candidates are also growing. The SLM/LLM emphasis system supports recruitment operations with advanced information processing capabilities while maintaining confidentiality. 【Usage Scenarios】 - Automatic screening of application documents - Assistance with interview evaluations - Providing personalized information to candidates 【Benefits of Implementation】 - Reduction in selection time - Alleviation of the burden on recruiters - Decrease in the risk of hiring mismatches

• Other information systems

In the IT industry, there is always a demand for improved development efficiency. In particular, an environment that allows for rapid code generation while ensuring security becomes a source of competitive advantage. The SLM/LLM emphasis system enables efficient code generation by handling sensitive information with a Local LLM (SLM) to ensure safety, while also leveraging the high inference performance of frontier LLMs. 【Use Cases】 - Code generation in a secure environment - Code generation based on internal documents - Integration with existing systems 【Benefits of Implementation】 - Reduction in development time - Decrease in security risks - Reduction in development costs

• Other information systems

In the real estate industry, accurate information gathering and analysis are essential for property evaluation. In particular, it is necessary to conduct advanced analysis while safely handling a wide range of information, including confidential property details, market trends, and legal regulations. The SLM/LLM emphasis system addresses these challenges. 【Use Cases】 * Property price assessment * Rent market analysis * Information gathering on surrounding areas 【Benefits of Implementation】 * Reduced risk of information leakage * Improved analysis accuracy * Increased operational efficiency

• Other information systems

In the entertainment industry, there is a demand for the rapid and safe production of diverse content. It is particularly important to mass-produce high-quality content while considering the risks of copyright protection and information leakage. The SLM/LLM emphasis system allows for handling confidential information with Local LLM (SLM) while also leveraging the high inference performance of Frontier LLM, enabling content production that balances security and performance. 【Use Cases】 - Scenario creation - Character setting - Dialogue generation - Content translation 【Benefits of Implementation】 - Reduction of information leakage risks - Rapid production of high-quality content - Cost reduction

• Other information systems

In the legal industry, document search requires accuracy and speed. Efficiently finding necessary information from a vast amount of legal documents greatly affects business efficiency. Decisions based on incorrect information can lead to significant risks. Our SLM/LLM emphasis system improves the search accuracy of legal documents and contributes to business efficiency. 【Use Cases】 - Case law search in law firms - Contract search in corporate legal departments - Investigation of litigation materials by lawyers 【Benefits of Implementation】 - Reduction in search time - Decrease in the risk of information leaks - Significant improvement in business efficiency

• Other information systems

In quality control within the manufacturing industry, it is important to detect product defects early and prevent the outflow of defective products. Particularly as manufacturing processes become more complex, quality control personnel need to detect anomalies from vast amounts of data and identify their causes. In response to this challenge, the SLM/LLM emphasis system streamlines quality control operations by handling confidential information with Local LLM while also leveraging the high inference performance of Frontier LLM. 【Use Cases】 - Anomaly detection in manufacturing sites - Report generation related to quality control - Searching product specifications and manuals 【Benefits of Implementation】 - Early detection and response to quality issues - Increased efficiency in quality control operations - Reduced risk of information leakage

• Other information systems

In the retail industry, prompt and accurate information provision is essential for customer service. Quickly providing accurate information in response to customer inquiries is crucial for improving customer satisfaction. However, when dealing with customer interactions that involve personal or confidential information, it is also necessary to consider the risk of information leakage. The SLM/LLM emphasis system achieves advanced customer service while ensuring security by combining Local LLM (SLM) and Frontier LLM. 【Usage Scenarios】 - FAQ responses - Chatbots - Inquiry handling 【Benefits of Implementation】 - Increased efficiency in customer service - Improved customer satisfaction - Reduced risk of information leakage

• Other information systems

In the field of individualized learning, detailed instruction tailored to each student's understanding and progress is required. Traditional uniform learning methods have posed challenges such as diminishing students' motivation to learn and advancing without sufficient understanding. The SLM/LLM emphasis system addresses these issues by analyzing students' learning data and generating learning content that meets individual needs. 【Usage Scenarios】 - Accurate answers to students' questions - Presentation of problems according to understanding levels - Summaries and reviews of learning content 【Effects of Implementation】 - Improved learning efficiency - Increased student motivation to learn - Reduced burden on teachers

• Other information systems

In the financial industry, advanced fraud detection systems are required to minimize losses from fraudulent transactions. In particular, the ability to detect anomalies in real-time is crucial to address increasingly sophisticated fraud and money laundering tactics. Cases that are difficult to handle with traditional rule-based systems can be quickly identified for new fraud patterns by our SLM/LLM emphasis system, which learns from past data. 【Use Cases】 - Fraud detection in financial transactions - Measures against money laundering - Risk assessment in credit screening 【Benefits of Implementation】 - Reduction in losses from fraudulent transactions - Improvement in fraud detection accuracy - Cost reduction through increased operational efficiency

• Other information systems

In the field of healthcare, diagnostic support requires the protection of patient confidentiality and accurate diagnoses based on the latest knowledge. In particular, it is important to balance the improvement of diagnostic accuracy with the protection of personal information. Our SLM/LLM emphasis system achieves this balance by handling confidential information with a Local LLM (SLM) while also leveraging the high reasoning performance of a frontier LLM. 【Use Cases】 - Image diagnostic support - Patient interview support - Diagnostic report creation 【Benefits of Implementation】 - Improved diagnostic accuracy - Reduced risk of information leakage - Increased operational efficiency

• Other information systems

**Features** 1) Balancing security and high performance Confidential information is handled on the Local LLM (SLM) side, while also leveraging the high inference performance of the Frontier LLM as needed. 2) Optimization tailored to business and industry It is easy to reflect specific domain knowledge such as internal documents, product information, and business flows, making it easier to meet unique demands that are difficult for general AI to address. 3) Support for fine-tuning and RAG Additional training or search integration of the Local LLM can be performed according to the application, improving response accuracy, consistency, and reproducibility. 4) Flexible system configuration It can be implemented in configurations that match the constraints and operational conditions of each company, including on-premises, cloud, and integration with existing business systems. 5) Support unique to contract development We provide consistent support from requirements organization to prototyping, implementation, evaluation, and improvement, finishing it in a form that can be used on-site.

• Other information systems

In the travel industry, there is a demand for flexible itinerary creation tailored to the needs of individual travelers. In particular, it is important to streamline complex tasks such as gathering information from diverse sources, optimizing transportation options, and selecting accommodations. LLFarM utilizes generative AI to address these challenges. 【Usage Scenarios】 - Information gathering in the initial stages of travel planning - Suggestions for transportation and accommodations - Itinerary optimization 【Benefits of Implementation】 - Reduction in time spent on travel planning - Creation of personalized itineraries based on diverse information - Increased traveler satisfaction

• Other information systems
• Other contract services

In the legal industry, accuracy and efficiency are required. Particularly in the creation of contracts, the precision of clauses, referencing past case law and similar cases, and prompt responses are crucial. Typos and misinterpretations can lead to significant legal risks. LLFarM utilizes generative AI to streamline the contract creation process. 【Use Cases】 - Drafting contracts - Extracting information from past contracts - Searching and referencing clauses - Summarizing contract contents 【Benefits of Implementation】 - Reduction in contract creation time - Risk mitigation through reduced errors - Effective utilization of knowledge - Significant improvement in operational efficiency

• Other information systems
• Other contract services

In the tourism industry, it is important to effectively convey the charm of the region and attract tourists. Engaging images, videos, and 3D content significantly contribute to raising awareness of tourist destinations and attracting visitors. However, there is a challenge in that producing high-quality content requires time and cost. DiFarsion, as a contract research and development brand specializing in image, video, and 3D generation AI, addresses these challenges. 【Usage Scenarios】 - Production of promotional videos for tourist destinations - Tourism experience content utilizing VR/AR - Virtual tours of tourist facilities using 3D models - Image generation for social media campaigns 【Benefits of Implementation】 - Increased attraction power through engaging content - Reduction in production costs and time - Information dissemination through diverse expressions - Differentiation through the latest technology

• Other information systems

We would like to introduce the case of "AIFARM." In 2025, we built a system consisting of LLM, RAG, image processing DNN, and UI. By combining it with our strength in deep learning models for images and videos, we can accurately obtain attributes of the target objects. [Case Overview] ■ A system consisting of LLM, RAG, image processing DNN, and UI has been built. ■ Capable of accurately obtaining attributes of target objects. *For more details, please download the PDF or feel free to contact us.

• Other services
• Other contract services

We would like to introduce the development achievements of Web Farmer Inc. In 2015, we developed our own deep learning framework called "DeepFarm," and in 2016, we researched and developed Double-DQN for deep reinforcement learning. In 2017, we conducted research and development on AI for real estate price prediction aimed at the real estate sector, as well as on animal behavior classification models. In 2024, we are conducting research and development on AI for medical ventures, and in 2025, we are also working on the research and development of systems using LLM. 【Development Achievements (Partial)】 ■ 2024: Research and development of a system using Local-LLM ■ 2024: Development of image generation AI ■ 2024 onwards: Research and development of AI for medical ventures ■ 2025 onwards: Development of systems using LLM ■ 2025: Research and development of systems using LLM *For more details, please download the PDF or feel free to contact us.

• others
• Other contract services

After 2024, "AIFARM" will create systems using LLM and RAG in a short period and at low cost. Based on our previous experience, we can also detect multimodal texts such as images and PDF documents with high accuracy. Additionally, we can retrain LLMs based on our years of experience in machine learning. [Features] ■ Create systems using LLM and RAG in a short period and at low cost ■ High-accuracy detection of multimodal texts ■ Retraining of LLMs is also possible *For more details, please download the PDF or feel free to contact us.

• Other information systems
• Other contract services

We will explain the reasons why our AI contract development and joint research service "AIFARM" is chosen. In addition to being able to develop all processes consistently from data generation to application development, our small elite team allows for low-cost and quick responses. We can also flexibly respond to frequent specification changes that occur during the POC phase. 【Reasons why AIFARM is chosen】 ■ Capable of developing AI through advanced research ■ Able to develop all processes consistently from data generation to application development ■ Low-cost and quick responses due to a small elite team ■ Flexible response to frequent specification changes during the POC phase *For more details, please download the PDF or feel free to contact us.

• others
• Other contract services

Web Farmer Inc. is engaged in the contracted development and joint research of AI systems, as well as the development of its own AI solutions. We have numerous publications, including the GAN Deep Learning Implementation Handbook and various other books related to artificial intelligence and data analysis, for which we have provided supervision and reviews. Please feel free to contact us when you need our services. 【Business Activities】 ■ Contracted development and joint research of AI systems: AIFARM ■ Development of in-house AI solutions: FAMMAL *For more details, please download the PDF or feel free to contact us.

• others
• Other contract services

In 2025, a system using AI agents was developed to streamline the operations of Company E. The AI agent understands the situation and plans the tools to be used. Based on this plan, inquiries to the LLM and RAG are executed. Both are repeatedly utilized based on the results. This process continues until the final output meets the required specifications. Programming language used: Python 3 Libraries used: Langgraph, Langchain Cloud: Azure *For more details, please refer to the related links or feel free to contact us.*

• Embedded system design service

In the medical system development project that our company is participating in, we are responsible for the research, development, and implementation of the AI components. To meet the precision and reliability required in the medical field, we are broadly engaged in the following tasks: ■ Research on relevant AI technologies ■ Design, development, and implementation of models ■ Training models using data ■ Verification of results and feedback Through these processes, we provide AI that supports the foundation of systems contributing to healthcare. We hope that many lives will be saved through our AI development. *For more details, please refer to the related links or feel free to contact us.*

• others

We have implemented improvements to the image generation AI model using the Diffusion model operated by Company E. The Diffusion model runs the model through multiple steps during inference, which generally results in longer inference times. This is one factor that can diminish the user experience. Our company has a deep understanding of model architecture developed over many years, as well as an understanding of the device, which has allowed us to achieve faster and lighter inference without compromising accuracy. (Image is from DDIM) *For more details, please refer to the related links or feel free to contact us.*

• others

In June 2024, we created an LLM for a certain company. In large corporations, the internal seeds have grown too large, making it difficult to generate new business ideas from them. This time, we developed a system where the LLM proposes new business ideas using the company's information A and another piece of information B. We used the open-source Llama model as the LLM. This allows the company to complete the work on-premises without disclosing information externally. To efficiently propose ideas, the system incorporates features like RAG and prompt modification. *For more details, please refer to the related links or feel free to contact us.*

• others

In March 2024, we performed optimization to adapt an AI model for a specific edge device for semiconductor-related company M. We implemented lightweight modifications to adapt it to a special device. This time, the device for inference required significant lightweight adjustments in terms of model size, so we started by reviewing the neural network architecture. After that, we performed quantization and pruning to make it adaptable to the specific device. As a result, we achieved a model that meets the speed and data capacity requirements for the specific device. *For more details, please refer to the related links or feel free to contact us.*

• others

In September 2022, we developed a system to promote DX for construction companies, as well as an AI system to read specific characters in business operations. This included everything from creating annotation tools to inference systems. We handled the creation of annotation tools, annotation, research, model implementation, training and evaluation, and the creation of the inference system. For the character recognition AI, we utilized an OCR service for part of the process, but we conducted preprocessing and correction using our proprietary AI before and after that. *For more details, please refer to the related links or feel free to contact us.*

• others

In 2022, we conducted analysis on information obtained from domestic companies' biological devices. From research on time-series data to the construction of an inference system. This time, since the subject was time-series data, we selected journals and conferences that corresponded to it and chose an appropriate Neural Network model architecture from those papers. Furthermore, we implemented the model, conducted training and evaluation, built the inference system, and visualized the results. Visualizing the results. Time-series data is difficult to visualize, but without appropriate visualization, evaluating the results becomes challenging. This time, we employed several methods to creatively visualize the data. *For more details, please refer to the related links or feel free to contact us.*

• others

In July 2022, we conducted research and development of an inference system using chemical sensors for domestic companies. From research to iPhone app development. This time, we started with literature research, followed by model implementation, training and evaluation, and the construction of the inference system, culminating in the app development for iPhone. We built a logic based on chemical research. This time, we dealt with substances in the AI industry that are considered a specialized field, specifically chemical sensors. Since there were no precedents for the inference model based on the output values, we thoroughly researched chemical literature and implemented a model that is chemically valid and highly explainable. We switched from Dart to Swift. Initially, the iPhone app was developed using the Dart programming language and Flutter. However, it became clear that some essential features could not be realized with Flutter, so we quickly switched to Swift. This allowed us to implement all the required features in the app. *For more details, please refer to the related links or feel free to contact us.*

• others

From 2021 to 2023, we conducted research and development on an AI system to be integrated into home appliances for Company I. We developed everything from annotation tool creation to inference system construction in a consistent manner. This included creating the annotation tool, performing annotations, conducting research, implementing models, training and evaluation, model optimization, building the inference system, and converting it for edge devices. We conducted research and implementation tailored to a specialized neural network architecture. The current neural network processes video and time-series data as input, so we researched models that accommodate this and implemented them based on past examples. We visualized the inference results. Since this development was at the POC stage, we sent the internal inference results to another computer and displayed the results in an easily understandable manner. This made debugging and improvements easier. *For more details, please refer to the related links or feel free to contact us.*

• others

In 2019, we developed a system for detecting and tracking specific substances in medical CT images for Company M. This involved creating an annotation tool, conducting research, implementing models, training and evaluation, and building an inference system. We created a proprietary tool. To meet the client's requirements, we needed special data, but there was no tool available for labeling it. Therefore, we independently developed an annotation tool and generated the data. Detection and tracking of special objects in unclear CT videos. In this case, the CT images in each frame of the video were coarse, making the detection and tracking of specific substances extremely challenging. However, we overcame this through improvements in the neural network architecture, innovations in image preprocessing, and enhancements to the tracking algorithm. *For more details, please refer to the related links or feel free to contact us.*

• others

From 2019 to 2023, we conducted research and development on an AI system to be integrated into beauty devices for Company H in Japan. This time, since there were no usable existing data, we started from data generation. We created an annotation tool and performed the annotation. Furthermore, we conducted research, implemented models, trained and evaluated them, reduced model size, and built an inference system. Due to the operational requirements of the hospitals using the devices, the allowed inference time per image was a few milliseconds. To achieve this, we carefully considered the architecture of the Neural Network and assembled an architecture that is ultra-fast yet reasonably accurate. The Neural Network architecture itself was made lightweight, but further reduction in size was necessary to meet the inference time on edge devices. Therefore, during the deployment phase, we performed pruning, distillation, and quantization. This allowed us to meet the required inference time. *For more details, please refer to the related links or feel free to contact us.*

• others

From 2018 to 2020, I conducted detection, tracking, position estimation, and behavior estimation of animals using AI. I developed everything from the creation of annotation tools to the construction and visualization of inference systems. At that time, detection, tracking, and behavior estimation of animals were fields where research was not advanced, so I started from creating annotation tools and performing annotations. Furthermore, I conducted research, implemented models, trained and evaluated them, and built and visualized inference systems. *For more details, please refer to the related links or feel free to contact us.*

• others

In April 2017, we researched and developed a model to predict real estate prices from structured data for real estate companies. From research to inference model creation. This time, we started with research that accommodates structured data and time series data, and proceeded to model implementation, training and evaluation, and the creation of an inference system. *For more details, please refer to the related links or feel free to contact us.*

• others

In 2018, we built an anomaly detection system for the production line of a food factory. In food production environments, the presence of impurities and unsanitary substances can become problematic. Therefore, a high recall inference system is required. From searching for appropriate models to implementation, training, and building the inference system, we researched suitable models and carried out their implementation, training, evaluation, and the construction of the inference system. To avoid existing patents, we developed a new model. Many companies are working on anomaly detection in this type of production line, and this time it was necessary to construct a new model that does not infringe on already filed patents. Thus, we conducted research at CVPR and ICCV and implemented a newly proposed type of anomaly detection model. *For more details, please refer to the related links or feel free to contact us.*

• Other production management systems

"AI Farm" is our brand that solves customer challenges with AI. Depending on the customer's situation, we conduct research on papers, data creation, annotation, model design, implementation, training, evaluation, model optimization, building inference systems, and app visualization. Additionally, if customers are unsure about what kind of system to use or want to implement advanced systems, we can also get involved from the research stage. [Achievements] ■ Tracking and individual identification of objects ■ Analysis using medical data ■ Analysis of time series data *For more details, please feel free to contact us.

• others