) Number-finger match (frequent search search "Buri") Number-finger match (Frequency search search) "Buri" 0000 (results and future prospects) (plan/method) Web search using GoogleTrends search function, etc. and news articles, etc., and build a database (prototype) integrated with the market prices of marine products.By doing this, we will extract issues in data integration. Statistically analyze the database (prototype) to quantitatively clarify changes in consumer fish eating culture and its factors.Apply exploratory approaches such as data visualization and interpretation using various data science methods.( Results and future prospects) Clarity, etc. is an issue for the next fiscal year and beyond.Sub-issue 5. Acquisition of data related to the distribution of marine products and analysis with AI (Midori Kawabe, Xanami Lou, Naotomo Nakahara, Takero Yoshida) (planning and Method) Sub-problem 5) Construction of an integrated database of market prices and social big data and AI analysis (Taro Oishi) The distribution of marine products is a complex structure involving many actors, as clearly indicated by its multi-stage nature. Although supply and demand for fresh fish is adjusted mainly through wholesale market distribution, various inefficiencies have been pointed out. By clarifying the price formation mechanism of marine products, we aim to provide information that contributes to the optimization of management behavior in the fishery and distribution industries, and to grasp the actual situation and collect data by fish type, region, and distribution stage. At the same time, we will explore new ways to utilize distribution data from the perspective of data science and AI, etc. We have constructed a database related to marine product distribution, keeping in mind the analysis using AI.Specifically, (1997) We collected daily catch data for the past five years for major domestic fish species and major production areas, and (100) collected daily trade data for the past five years for major fish species in wholesale markets in major consumption areas. Landing data includes type data such as fishing method, fishing ground, size, etc. for each fish type and production area Consumption area data includes data such as production area, size, market price, etc. For future database construction, POS We are planning to improve information on the retail stage using data, etc. In addition, we will collect qualitative information on management behavior at each stage of production and distribution, which could not be sufficiently advanced this year.We will update that information. At the same time, by conducting analysis using AI, we aim to clarify the price formation mechanism of marine products and build a price prediction model.The market price of fishery products is multidimensional large-scale data consisting of fish species, place of trade, stage of distribution (wholesale, retail, etc.), and changes over time.In this research, we will build a database (prototype) of social big data by integrating web data (web searches, SNS transmissions, etc.) that reflect consumer awareness and interests into such market price data.In addition, by analyzing the database, we will quantitatively analyze the impact of changes in consumer fish-eating culture and market prices (which are also indicators of resource scarcity) on fish-eating culture.This year, we built a social big data database (prototype).In addition, as a result of analyzing a part of the database, regarding salmon and amberjack, which have been pointed out by existing studies (Akitani (2004), etc.) to have strong regional characteristics in food culture, ``salmon'' is Hokkaido, and ``amberjack'' is Kagoshima. The relative frequency of web searches in major production areas such as Oita Prefecture and Oita Prefecture is high, suggesting that the search frequency reflects fish-eating culture to some extent (in fact, the keywords “fish species name” and “recipe” are used at the same time). many cases were found).In addition, regarding the search frequency of salmon and yellowtail (relative index with the prefecture with the highest frequency as 2019 [population adjusted]), the oldest available data (15) and the latest data before the COVID-10080604020 pandemic ( 47), the scatter of the data decreased over the 2040602004 years (Figure 47).It was suggested that the locality of fish-eating culture was reduced and homogenized during this period.Exploratory analysis of multivariate data including other fish species and solution of relationship with market price 8010010080604020 Frequency (relative index) 2040602019 (n=47) 80100 Search frequency for “salmon” (relative index) XNUMX (n=XNUMX) XNUMX.Acquisition of marine big data and promotion of AI analysis research (XNUMX) Development of a fishery integrated support system that realizes resilient and sustainable fisheries using marine organism big data and training of marine AI human resources
Original page ../index.html#26