With the help of multi-dimensional analysis cases of global university data, experience how TableAgent helps users easily gain insight into data and empower enterprises to achieve efficient digital transformation.

In the digital era, data analysis has become the basis for business decision-making, product optimization, operation improvement and other aspects. Whether you are a large enterprise or a startup, you need to use data analysis to understand market needs, optimize business processes, improve customer experience, etc. In this process, the TableAgent data analysis agent of Jiuzhang Yunji DataCanvas Company provides a brand-new solution to make data analysis simpler and more efficient.

1. Introduction to TableAgent and its advantages?

Jiuzhang Yunji DataCanvas Company is committed to providing users with basic artificial intelligence services through independently developed artificial intelligence basic software product series and solutions, helping users easily complete the two-way empowerment of models and data in the digital transformation, with low cost and high efficiency. Improve enterprise decision-making capabilities and realize large-scale application of enterprise-level AI.

TableAgent is an intelligent agent developed on the basis of the DataCanvas Alaya Jiuzhang Yuanshi large model that can realize privatized deployment of enterprise-level data analysis. It has very powerful intent understanding capabilities, analysis modeling capabilities and insights. After fully understanding the user's intentions, TableAgent independently uses advanced modeling technologies such as statistical science, machine learning, and causal inference to mine value from the data, and then provides insights to analyze opinions and guide actions, allowing users to more easily obtain data insights. .

Compared with other data analysis tools, TableAgent has the following advantages:

1. Conversational data analysis, what you need is what you get

TableAgent uses a conversational chat interface to input your analysis requirements. The system automatically completes data cleaning and data integration and gives you analysis results, saving a lot of time and energy.

2. Private deployment, data security

TableAgent provides privatized deployment for enterprises. The system is deployed within the enterprise and data is not leaked. It fundamentally solves the problem of security compliance, which is also a shortcoming of other foreign products.

3. Support enterprise-level data analysis, large scale, high performance

TableAgent can automatically perform data analysis and data mining based on data characteristics and business needs, discover patterns and trends in data, and support large-scale, high-performance enterprise-level data analysis.

4. Support field fine-tuning and specialization

TableAgent has designed a T+ (Table Family) system for this purpose, which can efficiently implement customized fine-tuning work. At the same time, the system has the ability to self-iterate. The systematic system supports more efficient upgrades in all aspects of data analysis, allowing users to Get an ever-upgrading data analysis experience without any awareness

5. Transparent process, audit deployment

TableAgent can view the answer generation process in real time, making the answer process transparent and facilitating audit deployment.

2. Use TableAgent to conduct multi-dimensional data analysis of global university data cases

In this session, bloggers will use the global college evaluation data set to question TableAgent in the following five dimensions to discover the value behind the data and provide decision-making for friends or companies seeking help in selecting schools for postgraduate entrance examinations/doctorate studies and analyzing school employment prospects. help.

1. Register

Register through TableAgent 's free public beta address . After registration, you can use it 5 times for free. Once the times are used up, you can apply for certification to increase the number of times (15 times per day).

2. Select the data set and import it

As shown in the figure below, we select [Global University Evaluation Data Set] and import it

3. Start asking 1: What data set is this and what is the meaning of each field?

After asking a question, you can see that you can get a quick answer and explain the fields in the data set. This is an evaluation data set about major universities around the world, including information on 1,422 universities.

4. Question 2 : How many institutions around the world are included in this data ? Count the number of schools in different countries and sort them in reverse order. Draw and interpret the top five ?

Starting our second question, we can see that tableAgent quickly answered our question:

In the data provided, there are a total of 1,422 schools. These schools are located in 100 different countries. Specifically, the United States has the most schools with 201, followed by the United Kingdom with 90, China with 71, Japan with 50, and Russia with 48.

Bar chart comparison of countries with top five universities by number of universities

From the above data and graphics, we can see that the United States and the United Kingdom are the two countries with the largest number of schools, occupying the top five positions respectively. China, Japan and Russia also have significant numbers of schools. This may reflect the relatively developed education systems of these countries, as well as the size of their populations.

5. Question 3 : Draw a diagram to analyze the three most important indicators of the top 10 universities in China, and briefly summarize the comparative analysis between them ?

Let’s start our third dimension of questioning: draw a picture to analyze the three most important indicators of China’s top 10 universities, and briefly summarize the comparative analysis between them?

When TableAgent intelligently generates answers, we can clearly see the generation process, which data analysis libraries and functions are used, and finally get the answer we want:

From the figure, we can more intuitively see the performance of these 10 universities under different indicators. For example, in the academic reputation indicator, the top-ranked university is Peking University, with an academic reputation score of 99.3, ranking 15th. In the employment prospects indicator, the top-ranked university is Tsinghua University, with an employment prospects score of 96.5, ranking 28th. In the international exchange indicator, the top-ranked university is Peking University, with an international exchange score of 34, ranking 28th.

Overall, China's top 10 universities perform well in terms of academic reputation, employment prospects, and international exchanges, which may mean that these universities are doing a good job of cultivating talents, providing employment opportunities, and attracting international students .

6. Question 4: From the data, does it mean that the higher the academic reputation score of a school, the better the employment prospect score?

Answer given by TableAgent:

According to data analysis, the correlation between the academic reputation score and the employment prospect score of the institution is 0.563519, which shows that there is a certain positive correlation between the academic reputation score and the employment prospect score. That is to say, the higher the academic reputation score, the higher the academic reputation score. The higher the college's employment prospects score. However, this correlation is not strong, so we cannot conclude that institutions with higher academic reputation scores will necessarily have better employment prospects.

We also plotted scatterplots for the academic reputation score and the employment prospects score to more visually see the relationship between them.

In general, although there is a certain positive correlation between academic reputation scores and employment prospect scores, this correlation is not strong. Therefore, we cannot simply think that institutions with higher academic reputation scores must have better employment prospects. good.

7. Question 5 : Schools are divided into three levels according to international level scores. Please provide an interpretation and summary of the drawing and comparison of schools at different levels in terms of academic reputation, teacher-student ratio, employment level, etc. ?

Answer given by TableAgent:

Lower-tier schools have an average academic reputation of 10.8416, a teacher-student ratio of 20.5826, and an employment level of 18.6315
For middle-level schools, the average academic reputation is 16.9779, the teacher-student ratio is 30.6251, and the employment level is 23.3316;
For high-level schools, the average academic reputation is 32.6798, the teacher-student ratio is 38.7643, and the employment level is 36.3253.

These data show that a school's level of internationalization has a significant impact on its academic reputation, teacher-student ratio and employment levels. Specifically, schools with a higher level of internationalization perform better in terms of academic reputation, teacher-student ratio, and employment level. This may be because these schools have greater internationalization pressure and are able to attract more international students. Students and staff will also be able to provide higher quality educational services. Schools with a lower level of internationalization have relatively lower academic reputations, teacher-student ratios, and employment levels. This may be because these schools do not have enough international pressure to attract more international students and faculty, and cannot Provide high-quality educational services.

8. Enlightenment

Through five-dimensional analysis and questioning of global university data set cases, TableAgent responds quickly, performs intelligent data analysis, and provides accurate answer decisions and reference charts, helping users deeply explore the value behind the data and provide guidance for those who are studying for further studies . Enterprises and individuals providing talent planning services provide convenient help and scientific decision-making support. Based on the overall experience, with its convenient operation, quick response, and accurate replies, TableAgent is undoubtedly the first choice for intelligent data analysis products.

3. Compare other products

product	TableAgent	Wen Xin Yi Yan - E Yan Yi Picture	Code Interpreter
interactive form	Conversational	Conversational	Conversational
data processing	The processing process is transparent, and users can clearly understand the specific steps and results of data processing, which facilitates auditing and supervision.	Focus on data visualization and simplified operations	Users can see the specific steps and results of data processing in real time
data analysis	Able to autonomously use advanced modeling techniques such as statistical science, machine learning, and causal inference to extract value from data to provide insights and guide actions.	Suitable for rapid analysis and visualization of small-scale data	Ability to autonomously leverage advanced modeling techniques such as statistical science, machine learning, and causal inference to extract value from data
Chart generation	support	support	support
code generation	Code can be automatically generated	Achieve by dragging and configuring	Code can be automatically generated
Can it be deployed privately?	Provide privatized deployment, the system is deployed within the enterprise, and the data is not leaked, fundamentally solving the problem of security and compliance.	unknown	Not supported, there are risks such as enterprise data security and compliance
Private deployment hardware requirements	Low computing power consumption	unknown	Private is not supported

4. Summary

In the digital age, the importance of data analysis is as ubiquitous as the air. Business data analysis is the foundation of digital management and intelligent decision-making. At the same time, data analysis is a highly professional job. Descriptive analysis, diagnostic analysis, and predictive analysis will be daunting to most people who can only use Excel. The TableAgent data analysis agent independently developed by Jiuzhang Yunji DataCanvas allows large models to empower personal productivity and enterprise intelligent transformation, rising from data analysis and providing assisted decision-making to a new level. As long as you can ask questions, you can become a A senior data analyst with insight into the mysteries of data. At the same time, TableAgent will further integrate the analysis capabilities of unstructured data in the future, and jointly innovate with the company's self-developed DingoDB multi-modal vector database and DataCanvas Alaya nine-piece metadata model. In the future, there will be further upgrades in complex analysis tasks, automation, human-computer interaction, and intelligent agent collaboration.