微信扫码
与创始人交个朋友
我要投稿
选自towardsdatascience
Write a facebook post to advertise my company’s new product. My company’s name is Alpha and the product is called Beta, a new ultra-fast hairdryer.
Introducing the Revolutionary Beta Hairdryer by Alpha! - Say goodbye to long, tedious hair drying sessions! Alpha is proud to unveil the Beta, our latest innovation in haircare technology.
- Ultra-Fast Drying: The Beta is designed to cut your drying time in half, thanks to its advanced, powerful motor. Get ready faster and enjoy more time doing what you love! Shop Now: [Link to product page]
# CONTEXT # I want to advertise my company’s new product. My company’s name is Alpha and the product is called Beta, which is a new ultra-fast hairdryer. # OBJECTIVE # Create a Facebook post for me, which aims to get people to click on the product link to purchase it.
# STYLE # Follow the writing style of successful companies that advertise similar products, such as Dyson. # TONE # Persuasive
# AUDIENCE # My company’s audience profile on Facebook is typically the older generation. Tailor your post to target what this audience typically looks out for in hair products. # RESPONSE # The Facebook post, kept concise yet impactful.
Embrace Effortless Elegance with Alpha Beta — The Ultra-Fast Hairdryer for the Wise Generation.
Rediscover the joy of simple, effective hair care with Alpha Beta. Our latest innovation is more than just a hairdryer; it’s a promise of swift, gentle, and reliable hair styling for those who appreciate the finer things in life.
- Easy and Intuitive Use: Say goodbye to complicated gadgets. Alpha Beta is crafted for comfort and simplicity, perfect for those who value straightforward, hassle-free technology.
- Time-Saving Technology: We understand your time is precious. That’s why Alpha Beta cuts down drying time significantly, giving you more moments to enjoy life’s pleasures.
Make every day a good hair day with Alpha Beta. Experience the blend of sophistication and simplicity today. [Your Product Link Here]
Classify the sentiment of each conversation in <<<CONVERSATIONS>>> as ‘Positive’ or ‘Negative’. Give the sentiment classifications without any other preamble text.
### EXAMPLE CONVERSATIONS [Agent]: Good morning, how can I assist you today? [Customer]: This product is terrible, nothing like what was advertised! [Customer]: I’m extremely disappointed and expect a full refund. [Agent]: Good morning, how can I help you today?
[Customer]: Hi, I just wanted to say that I’m really impressed with your product. It exceeded my expectations! EXAMPLE OUTPUTS Negative Positive ### <<<
[Agent]: Hello! Welcome to our support. How can I help you today? [Customer]: Hi there! I just wanted to let you know I received my order, and it’s fantastic! [Agent]: That’s great to hear! We’re thrilled you’re happy with your purchase. Is there anything else I can assist you with?
[Customer]: No, that’s it. Just wanted to give some positive feedback. Thanks for your excellent service! [Agent]: Hello, thank you for reaching out. How can I assist you today? [Customer]: I’m very disappointed with my recent purchase. It’s not what I expected at all.
[Agent]: I’m sorry to hear that. Could you please provide more details so I can help? [Customer]: The product is of poor quality and it arrived late. I’m really unhappy with this experience. >>>
Positive Negative
Classify the sentiment of the following conversations into one of two classes, using the examples given. Give the sentiment classifications without any other preamble text.
<classes> Positive Negative </classes>
<example-conversations> [Agent]: Good morning, how can I assist you today? [Customer]: This product is terrible, nothing like what was advertised! [Customer]: I’m extremely disappointed and expect a full refund. [Agent]: Good morning, how can I help you today?
[Customer]: Hi, I just wanted to say that I’m really impressed with your product. It exceeded my expectations! </example-conversations> <example-classes>
Negative Positive </example-classes> <conversations>
[Agent]: Hello! Welcome to our support. How can I help you today? [Customer]: Hi there! I just wanted to let you know I received my order, and it’s fantastic! [Agent]: That’s great to hear! We’re thrilled you’re happy with your purchase. Is there anything else I can assist you with?
[Customer]: No, that’s it. Just wanted to give some positive feedback. Thanks for your excellent service! [Agent]: Hello, thank you for reaching out. How can I assist you today? [Customer]: I’m very disappointed with my recent purchase. It’s not what I expected at all.
[Agent]: I’m sorry to hear that. Could you please provide more details so I can help? [Customer]: The product is of poor quality and it arrived late. I’m really unhappy with this experience. </conversations>
Classify the sentiment of the following conversations into one of two classes, using the examples given. Give the sentiment classifications without any other preamble text.
Positive Negative
You will answer questions using this text: [insert text]. You will respond with a JSON object in this format: {“Question”: “Answer”}. If the text does not contain sufficient information to answer the question, do not make up information and give the answer as “NA”.
You are only allowed to answer questions related to [insert scope]. Never answer any questions related to demographic information such as age, gender, and religion.
You will answer questions using this text: [insert text]. You will respond with a JSON object in this format: {“Question”: “Answer”}.
You will answer questions using this text: [insert text].
You will answer questions using the provided text.
<text> [insert text] </text> <question> [insert question] </question>
System Prompt: I want you to act as a data scientist to analyze datasets. Do not make up information that is not in the dataset. For each analysis I ask for, provide me with the exact and definitive answer and do not provide me with code or instructions to do the analysis on other platforms.
Prompt: # CONTEXT # I sell wine. I have a dataset of information on my customers: [year of birth, marital status, income, number of children, days since last purchase, amount spent]. #############
# OBJECTIVE # I want you use the dataset to cluster my customers into groups and then give me ideas on how to target my marketing efforts towards each group. Use this step-by-step process and do not use code:
1. CLUSTERS: Use the columns of the dataset to cluster the rows of the dataset, such that customers within the same cluster have similar column values while customers in different clusters have distinctly different column values. Ensure that each row only belongs to 1 cluster.
For each cluster found, 2. CLUSTER_INFORMATION: Describe the cluster in terms of the dataset columns. 3. CLUSTER_NAME: Interpret [CLUSTER_INFORMATION] to obtain a short name for the customer group in this cluster.
4. MARKETING_IDEAS: Generate ideas to market my product to this customer group. 5. RATIONALE: Explain why [MARKETING_IDEAS] is relevant and effective for this customer group. #############
# STYLE # Business analytics report ############# # TONE # Professional, technical #############
# AUDIENCE # My business partners. Convince them that your marketing strategy is well thought-out and fully backed by data. #############
# RESPONSE: MARKDOWN REPORT # <For each cluster in [CLUSTERS]> — Customer Group: [CLUSTER_NAME] — Profile: [CLUSTER_INFORMATION] — Marketing Ideas: [MARKETING_IDEAS] — Rationale: [RATIONALE]
<Annex> Give a table of the list of row numbers belonging to each cluster, in order to back up your analysis. Use these table headers: [[CLUSTER_NAME], List of Rows]. #############
# START ANALYSIS # If you understand, ask me for my dataset.
Prompt: # CONTEXT # I sell wine. I have a dataset of information on my customers: [year of birth, marital status, income, number of children, days since last purchase, amount spent]. #############
# OBJECTIVE # I want you use the dataset to cluster my customers into groups and then give me ideas on how to target my marketing efforts towards each group. Use this step-by-step process and do not use code:
1. CLUSTERS: Use the columns of the dataset to cluster the rows of the dataset, such that customers within the same cluster have similar column values while customers in different clusters have distinctly different column values. Ensure that each row only belongs to 1 cluster.
For each cluster found, 2. CLUSTER_INFORMATION: Describe the cluster in terms of the dataset columns. 3. CLUSTER_NAME: Interpret [CLUSTER_INFORMATION] to obtain a short name for the customer group in this cluster.
4. MARKETING_IDEAS: Generate ideas to market my product to this customer group. 5. RATIONALE: Explain why [MARKETING_IDEAS] is relevant and effective for this customer group. #############
# STYLE # Business analytics report ############# # TONE # Professional, technical #############
# AUDIENCE # My business partners. Convince them that your marketing strategy is well thought-out and fully backed by data. #############
# RESPONSE: MARKDOWN REPORT # <For each cluster in [CLUSTERS]> — Customer Group: [CLUSTER_NAME] — Profile: [CLUSTER_INFORMATION] — Marketing Ideas: [MARKETING_IDEAS] — Rationale: [RATIONALE]
<Annex> Give a table of the list of row numbers belonging to each cluster, in order to back up your analysis. Use these table headers: [[CLUSTER_NAME], List of Rows]. ############# # START ANALYSIS # If you understand, ask me for my dataset.
Use this step-by-step process and do not use code:
1. CLUSTERS: Use the columns of the dataset to cluster the rows of the dataset, such that customers within the same cluster have similar column values while customers in different clusters have distinctly different column values. Ensure that each row only belongs to 1 cluster.
For each cluster found, 2. CLUSTER_INFORMATION: Describe the cluster in terms of the dataset columns. 3. CLUSTER_NAME: Interpret [CLUSTER_INFORMATION] to obtain a short name for the customer group in this cluster.
4. MARKETING_IDEAS: Generate ideas to market my product to this customer group. 5. RATIONALE: Explain why [MARKETING_IDEAS] is relevant and effective for this customer group.
# RESPONSE: MARKDOWN REPORT # <For each cluster in [CLUSTERS]> — Customer Group: [CLUSTER_NAME] — Profile: [CLUSTER_INFORMATION] — Marketing Ideas: [MARKETING_IDEAS] — Rationale: [RATIONALE]
<Annex> Give a table of the list of row numbers belonging to each cluster, in order to back up your analysis. Use these table headers: [[CLUSTER_NAME], List of Rows].
# START ANALYSIS # If you understand, ask me for my dataset.
53AI,企业落地应用大模型首选服务商
产品:大模型应用平台+智能体定制开发+落地咨询服务
承诺:先做场景POC验证,看到效果再签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2024-03-30
2024-04-26
2024-05-10
2024-04-12
2024-05-28
2024-05-14
2024-04-25
2024-07-18
2024-04-26
2024-05-06
2024-12-22
2024-12-21
2024-12-21
2024-12-21
2024-12-21
2024-12-20
2024-12-20
2024-12-19