Tokyo Seimitsu has been granted a patent for a prober controlling device that enhances the precision of probe needle positioning on semiconductor chips. The device utilizes temperature data and a machine learning model to predict and determine the optimal contact position of the probe needles. GlobalData’s report on Tokyo Seimitsu gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Tokyo Seimitsu, Welding robots was a key innovation area identified from patents. Tokyo Seimitsu's grant share as of June 2024 was 48%. Grant share is based on the ratio of number of grants to total number of patents.

Prober controlling device for semiconductor chip testing

Source: United States Patent and Trademark Office (USPTO). Credit: Tokyo Seimitsu Co Ltd

The patent US12007413B2 describes a prober controlling device designed to enhance the precision of semiconductor chip probing. The device integrates several components, including a wafer chuck for holding the wafer, a probe card with probe needles, and a relative moving unit that facilitates the movement of the wafer chuck in relation to the probe needles. Central to the device's functionality is an input data acquiring unit that collects various data, including temperature data from the probe card and card holder. A predicting unit utilizes this data to forecast the position of the probe needle's tip, while a determining unit assesses whether to proceed with the prediction based on comparisons between the acquired input data and previously established teacher data used for machine learning.

Further elaboration on the device's capabilities reveals that if the determining unit opts against executing the prediction, a needle position acquiring unit can gather the actual position of the probe needle. This information is then used by a relearning unit to update the prediction model, ensuring continuous improvement in accuracy. The device also includes provisions for excluding outdated data during the relearning process. When the prediction is deemed appropriate, the movement controlling unit adjusts the relative moving unit based on the predicted position, enabling precise contact between the probe needle and the semiconductor chip. The prober controlling method outlined in the patent mirrors these functionalities, emphasizing the systematic approach to data acquisition, prediction, and decision-making in the probing process.

To know more about GlobalData’s detailed insights on Tokyo Seimitsu, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.