Content industry - Artificial Intelligence Recommendation

Overview

This topic describes the data specifications for the content industry. You must comply with these specifications when you upload historical data and real-time data.

Data description

For scenes in the content industry, you must prepare the following three data tables:

Item table: This table contains all the recent items that can be recommended for the current scene. The term item refers to content in this topic.
The items that can be added have a quota limit. We recommend that you deduplicate items before you upload the table.
The item_id and item_type fields are used together to uniquely identify an item.
User table: This table contains all users who have recently registered on the system.
The users that can be added have a quota limit. We recommend that you deduplicate users before you upload the table.
You can use the imei field or a combination of the user_id and imei fields to uniquely identify a user. For example, in the latter case, you can use the user_id field to identify users who have logged on and use the imei field to identify users who have not logged on.
Make sure that all users are unique. When you request recommendation results, you must specify the unique identifiers of users. Otherwise, personalized recommendations cannot be achieved.
Behavior table: This table contains recent behavior data in the current scene.
We recommend that you provide behavior data of the last one to two weeks. If behavior data cannot be provided due to technical reasons or no historical data is available because the scene is new, you can use the test data provided by Artificial Intelligence Recommendation (AIRec). In this case, the recommendation model may return results that do not meet your requirements in the next two weeks. The recommendation becomes more precise as data is accumulated. We recommend that you specify as many optional fields in the tables as possible.
The more valid optional fields you specify, the better the recommendation results are. If an optional field is not specified, the system uses its default value.

Table schema

Important

1. You must specify the fields that are marked as Required in the Required column of the following tables. The fields that are marked as Required and Recommended in the Required column have significant impacts on the recommendation results. The fields are described in the Value description column.

2. Data is required to start an AIRec instance. You can use a MaxCompute table to upload historical data to start an AIRec instance. In this case, you can leave optional fields empty in the table. However, the table must contain all fields. For more information about the statements to create a table, see the "CREATE TABLE statements" section of this topic.

Item

Field name	Data type	Required	Field description	Valid value	Value description	Example
item_id	string	Required	The unique ID of an item. The value can contain only letters and digits.	Custom	1. The item_id and item_type fields uniquely identify an item. 2. The value of the item_id field can be up to 50 characters in length. Note: The reported item IDs must be recorded for later use.	34513
item_type	string	Required	The type of the item.	image, article, video, shortvideo, item, recipe, and audio. If the enumerated values do not meet your business requirements, contact technical support.	The uploaded data must match the specified item type. Otherwise, mixed sorting does not take effect.	article
status	string	Required	Specifies whether the item can be recommended.	0 and 1	1: The item can be recommended. 0: The item cannot be recommended. Note: 1. If you change the value from 0 to 1, the item is immediately added to the recommendation list. 2. If you change the value from 1 to 0, the item is immediately removed from the list.	1
scene_id	string	Required	The ID of the scene. Items are recommended to different scenes. Scenes vary based on the types of users and web pages.	Custom	1. We recommend that you use an acronym or a combination of letters and digits. 2. Do not use colons (:). 3. Do not set this field to -102. This value is an internal value reserved by the system. 4. If only one scene is available, set this field to 1. 5. You can set this field to multiple scene IDs and separate them with commas (,). The scene IDs match different web pages to which the item is recommended. For more information, see Use scene IDs.	a101,b102
duration	string	Required for the video industry and optional for other industries	The length of the video. The value must be greater than or equal to 0 and less than 36000. Unit: seconds.	Custom	The length of the video.	1000
pub_time	string	Required	The time at which the item is released. The value is a UNIX timestamp that is accurate to the second. This field is used to determine whether the item is the latest item.	Custom	If you have high requirements for timeliness, this field is required. This field is used for the recommendation of new items.	1520327038
expire_time	string	Recommended	The time at which the item expires. The value is a UNIX timestamp that is accurate to the second.	Custom	1. If the current system time of your server is later than the value of this field, the item is expired and no longer recommended. 2. If all items in the table expire, the service cannot be started. 3. If this field is left empty, the item never expires.	1520327038
last_modify_time	string	Optional	The time at which the item information was last modified. The value is a UNIX timestamp that is accurate to the second.	Custom	If you make major updates to a released item and have high requirements for timeliness, you can update this field. This field is similar to pub_time. Both of the fields are used to identify new items.	1520327038
title	string	Recommended	The title of the item.	Custom	This field is used for in-depth semantic analysis. If this field is left empty, some results of the algorithm may be lost. We recommend that you set this field.	The Digital Era Provides the Greatest Opportunity
weight	string	Recommended	Specifies whether the item is weighted. Note: 1. For a weighted item, set this field to 100. For an unweighted item, set this field to 1. 2. You must set this field to 100 or 1. Other values are invalid. 3. We recommend that you keep the number of weighted items less than or equal to 10% of the total number of items.	Custom	1. If you leave this field empty, the default value 1 is used. 2. A weighted item is more likely to be recommended.	1
category_level	string	Recommended	The category level, such as level 3.	Custom	If this value does not match the value of the category_path field, the discretization feature is affected.	3
category_path	string	Recommended	The category path, with categories separated by underscores (_).	Custom	1. A category path can contain multiple categories. You must separate the categories with underscores (_). 2. Commas (,) or colons (:) are not allowed. Category paths are used in discretization policies.	12_1024_56
tags	string	Recommended	The tags of the item. Separate multiple tags with commas (,).	Custom	1. Tags are used to describe the characteristics of items. You must manage your own tag library. 2. The algorithm model performs characteristic analysis based on tags. 3. You can create a maximum of 100 tags for a single item. We recommend that you do not create more than 50,000 tags in each tag pool. 4. If tags are confidential business data, we recommend that you convert the tags into digits based on the related mapping rules and upload the desensitized data.	digitalization, artificial intelligence, AI
author	string	Recommended	The author.	Custom	1. Separate multiple authors with commas (,). A single item can have a maximum of 100 authors. 2. Discretization can be implemented based on authors.	Tom
content	string	Optional	The body part of the item.	Custom	You can set this field to the key segment of the content. A maximum of 5,000 characters are allowed. This field is used for semantic analysis.	The High-level Panel on Digital Cooperation submitted its report "The Age of Digital Interdependence" to the UN Secretary-General on Monday, June 10, 2019. Jack Ma, co-chairman of the High-level Panel on Digital Cooperation, said, "I believe the digital era is the greatest opportunity for us. The biggest risk is missing this grand opportunity."
channel	string	Recommended	The channel to which the content belongs, such as economy. One item has only one channel.	Custom
organization	string	Optional	The organizations. Separate multiple organizations with commas (,).	Custom
pv_cnt	string	Optional	The number of exposures in one month.	Custom	During service start, if behavior data in the current scene is sparse, you can add behavior data of other scenes to this field. Non-real-time data is acceptable. If the maintenance cost of these fields is high after the model becomes stable, you can process them at a low priority.	100000
click_cnt	string	Optional	The number of clicks in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	1000
like_cnt	string	Optional	The number of likes in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
unlike_cnt	string	Optional	The number of dislikes in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
comment_cnt	string	Optional	The number of comments in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
collect_cnt	string	Optional	The number of favorites in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
share_cnt	string	Optional	The number of shares in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
download_cnt	string	Optional	The number of downloads in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
tip_cnt	string	Optional	The number of rewards in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
subscribe_cnt	string	Optional	The number of follows in one month.	Custom	Non-real-time data is acceptable. You can process this field at a low priority.	100
source_id	string	Optional	The platform by which the item is released to the scene.	Custom	For example, you can use 1 to indicate Taobao and 2 to indicate Tmall.	1
country	string	Optional	The code of the country.	Custom	Set this field to an ISO 3166-1 alpha-3 code.	CHN
city	string	Optional	The name of the city.	Custom		Hangzhou or Shanghai
features	string	Optional	The item characteristics, which are strings.	Custom	Separate item characteristics with commas (,). The characteristics must be descriptive.
num_features	string	Optional	The item characteristics, which are numerical values.	Custom	Separate item characteristics with commas (,). Make sure that the number of commas (,) in this field is the same for all items.

User

Field name	Data type	Required	Field description	Valid value	Value description	Example
user_id	string	Required for users who have logged on	The unique ID of a user.	Custom	1. This field is required for users who have registered. 2. This field uniquely identifies a user.	1234567
user_id_type	string	Optional	The registration type of the user.	1234	1: app account. 2: mobile phone number. 3: WeChat account. 4: other.	2
imei	string	Required for users who have not logged on	For an Android user, set this field to the MD5 hash value of International Mobile Equipment Identity (IMEI). For an iOS user, set this field to the MD5 hash value of Identifier for Advertisers (IDFA).	Custom	1. This field is required for users who have not registered. 2. If the MAC address or the device number is invalid, internal customer portrait information cannot be used. Only the exposure blocking feature is retained.	MD5 hash value of IMEI 358800091015835: 74f25e604e1a9dde7471fe2e25ae54d0, MD5 hash value of IDFA 41B2FD07-695A-4A27-8D26-C30ECE6F7EAD: 06e1565409c9fc4887036b97442135ee
third_user_name	string	Optional	The name of a third-party user.	Custom		jack
third_user_type	string	Optional	The name of the third-party platform.	Custom		wechat
phone_md5	string	Optional	The MD5 hash value of a mobile phone number. The value must be 32 characters in length.	Custom		d41d8cd98f00b204e9800998ecf8427e
gender	string	Optional	The gender of the user.	male, female, and unknown	If gender information is sensitive, you can use digits. For example, use 0 to indicate male, 1 to indicate female, and 2 to indicate unknown.	male
age	string	Optional	The age of the user.	Custom		22
age_group	string	Optional	The age group.	Custom		20-25
country	string	Optional	The code of the country.	Custom	Set this field to an ISO 3166-1 alpha-3 code.	CHN
city	string	Optional	The name of the city.	Custom		Hangzhou or Shanghai
ip	string	Optional	The last logon IP address.	Custom		202.113.XX.XX
device_model	string	Optional	The device model.	Custom		iphoneX
tags	string	Optional	User tags. Separate multiple tags with commas (,).	Custom	Use tags to describe the user.	football, fitness, outdoor
source	string	Optional	The source of the user.	Custom		Toutiao
content	string	Optional	The description of the user.	Custom
register_time	string	Optional	The registration time. The value is a UNIX timestamp that is accurate to the second.	Custom		1520007038
last_login_time	string	Optional	The last logon time. The value is a UNIX timestamp that is accurate to the second.	Custom		1520017038
last_modify_time	string	Optional	The time at which the user information was last modified. The value is a UNIX timestamp that is accurate to the second.	Custom		1520327038
features	string	Optional	The user characteristics, which are strings.	Custom	Separate the user characteristics, such as customer portraits, with commas (,).
num_features	string	Optional	The user characteristics, which are numerical values.	Custom	Separate user characteristics with commas (,). Make sure that the number of commas (,) in this field is the same for all users.

Behavior

Field name	Data type	Required	Field description	Valid value	Value description	Example
item_id	string	Required	The ID of the item.	Custom	The value must be the same as the value of the item_id field in the item table.	34513
item_type	string	Required	The type of the item.	image, article, video, shortvideo, item, recipe, and audio	The value must be consistent with the value of the item_type field in the item table.	image
bhv_type	string	Required	The behavior type, such as expose, stay, click, collect, and download.	expose and click	The number of click entries must be less than the number of expose entries. Otherwise, the system may determine that the data is abnormal, and the service cannot be started.	expose
trace_id	string	Required	The request tracking ID. This field is used in A/B testing to determine whether an Alibaba recommendation engine is used.	Alibaba and selfhold	1. If the behavior data is generated based on an Alibaba recommendation engine, set this field to Alibaba. If the behavior data is generated based on a self-developed or self-operated recommendation system, set this field to selfhold. 2. This field is used to generate analytical reports and compare the results in the console.	Alibaba
trace_info	string	Required	The request tracking information. The information is used for internal link tuning in AIRec.	Custom	1. If the trace_id field is set to selfhold, set the trace_info field to 1. 2. If the trace_id field is set to Alibaba, trace_info is returned in the recommendation result. The value Alibaba indicates that the behavior is performed on an item that is recommended by AIRec. When you upload behavior data, you can retain the value of the trace_info field for this item.	1007.5911.12351.1002000:4ea8bc59-aa9c-11b85be7:46:recommend:5:life:::10:content___5f3b2404c115eac:article:hot_common:0.0869:0.20308921:0.69352831:159895::::::::::
scene_id	string	Required	The ID of the scene.	Custom	1. The ID of the scene where the behavior entry is generated. The value must be one of the scene IDs for the item that corresponds to the behavior. Only one scene ID is allowed. 2. The value of the scene_id field in the behavior table must be included in the value of the scene_id field in the item table. 3. If you do not need to distinguish between scenes, use the default value 1. If the scene ID of the behavior cannot be traced, set this field to -102. For more information, see Use scene IDs.	a101
bhv_time	string	Optional	The time at which the behavior occurs. The value is a UNIX timestamp that is accurate to the second.	Custom	Set this field to the time when the user performs the behavior.	1520327038
bhv_value	string	Required	Behavior details, such as the number of clicks, time spent on the page, and number of purchased items.	Custom	1. For exposures, clicks, and shares, set this field to 1. 2. For stays, specify the time spent on the page. Unit: seconds. 3. For other behaviors, contact technical support.	500
user_id	string	Required for users who have logged on	The ID of the user.	Custom	1. The value must be the same as that in the user table. 2. If the user has not logged on, you can leave this field empty.	1234567
platform	string	Optional	The client platform.	Custom	ios/android/h5	ios
imei	string	Required for users who have not logged on	For an Android user, set this field to the MD5 hash value of IMEI. For an iOS user, set this field to the MD5 hash value of IDFA.	Custom	1. This field is required for users who have not registered. 2. If the MAC address or the device number is invalid, internal customer portrait information cannot be used. Only the exposure blocking feature is retained. 3. The value must be an MD5 hash value with 32 characters in length.	e2fcdb0f4dce45e35fe2823d797333ec
app_version	string	Optional	The version number of the app.	Custom		4.1.10
net_type	string	Optional	The type of the network.	Custom	2G/3G/4G/WIFI	4G
ip	string	Optional	The IP address of the client.	Custom		234.45.13.14
login	string	Optional	Specifies whether the user has logged on.	01	0: The user has not logged on. 1: The user has logged on.	1
report_src	string	Optional	The source of the report.	12	1: the server. 2: the client.	2
device_model	string	Optional	The device model.	Custom		iphoneX
longitude	string	Optional	The longitude.	Custom		128.4
latitude	string	Optional	The latitude.	Custom		78.1
module_id	string	Optional	The ID of the module.	Custom		114
page_id	string	Optional	The ID of the page.	Custom		4
position	string	Optional	The position of the item.	Custom		5
message_id	string	Optional	The unique identifier of a behavior entry.	Custom	If you do not set this field, the system uses the item_id, item_type, user_id, imei, bhv_type, and bhv_time fields to deduplicate behavior entries.	5

Behavior type

bhv_type	Description
expose	The "expose" behavior on an item. The behavior table must contain expose entries. The number of expose entries must be greater than the number of click entries.
click	The "click" behavior on an item. The behavior table must contain click entries.
like	The "like" behavior on an item.
unlike	The "dislike" behavior on an item.
comment	The "comment" behavior on an item.
collect	The "favorite" behavior on an item.
stay	The "stay" behavior on an item.
share	The "share" behavior on an item.
download	The "download" behavior on an item.
tip	The "reward" behavior on an item.
subscribe	The "follow" behavior on an item.
dislike	The behavior of providing negative feedback. For more information, see Negative feedback.
page_next	The behavior of turning to the next page. Set the bhv_value field to 1.

CREATE TABLE statements

If you use MaxCompute to upload data required for starting an AIRec instance, you can refer to the following CREATE TABLE statements:

--- Create a behavior table in the content industry.
DROP TABLE IF EXISTS behavior_table;
CREATE TABLE IF NOT EXISTS `behavior_table`
(
    trace_id STRING COMMENT "Request tracking ID"
    ,trace_info STRING COMMENT "Request tracking information"
    ,platform STRING COMMENT "Client platform"
    ,device_model STRING COMMENT "Device model"
    ,imei STRING COMMENT "Device ID"
    ,app_version STRING COMMENT "App version number"
    ,net_type STRING COMMENT "Network type"
    ,longitude STRING COMMENT "Longitude"
    ,latitude STRING COMMENT "Latitude"
    ,ip STRING COMMENT "Client IP address"
    ,login STRING COMMENT "Whether the user has logged on"
    ,report_src STRING COMMENT "Source of the report"
    ,scene_id STRING COMMENT "Scene ID"
    ,user_id STRING COMMENT "User ID"
    ,item_id STRING COMMENT "Item ID"
    ,item_type STRING COMMENT "Type of the item"
    ,module_id STRING COMMENT "Module ID"
    ,page_id STRING COMMENT "Page ID"
    ,position STRING COMMENT "Position of the item"
    ,bhv_type STRING COMMENT "Behavior type"
    ,bhv_value STRING COMMENT "Behavior details"
    ,bhv_time STRING COMMENT "Time at which the behavior occurs"
)
PARTITIONED BY 
(
    ds STRING
)
LIFECYCLE 30
;


--- Create a user table in the content industry.
DROP TABLE IF EXISTS user_table;
CREATE TABLE IF NOT EXISTS `user_table`
(
    user_id STRING COMMENT "Unique user ID"
    ,user_id_type STRING COMMENT "Registration type of the user"
    ,third_user_name STRING COMMENT "Name of the third-party user"
    ,third_user_type STRING COMMENT "Name of the third-party platform"
    ,phone_md5 STRING COMMENT "MD5 hash value of the mobile phone number of the user."
    ,imei STRING COMMENT "Device ID of the user"
    ,content STRING COMMENT "User content"
    ,gender STRING COMMENT "Gender"
    ,age STRING COMMENT "Age"
    ,age_group STRING COMMENT "Age group"
    ,country STRING COMMENT "Country"
    ,city STRING COMMENT "City"
    ,ip STRING COMMENT "Last logon IP address"
    ,device_model STRING COMMENT "Device model"
    ,register_time STRING COMMENT "Registration time"
    ,last_login_time STRING COMMENT "Last logon time"
    ,last_modify_time STRING COMMENT "Last modification time of user information"
    ,tags STRING COMMENT "User tags"
    ,source STRING COMMENT "Source of the user"
    ,features STRING COMMENT "Additional user characteristics, which are strings"
    ,num_features STRING COMMENT "Additional user characteristics, which are numerical values"
)
PARTITIONED BY 
(
    ds STRING
)
LIFECYCLE 30
;


--- Create an item table in the content industry.
DROP TABLE IF EXISTS item_table;
CREATE TABLE IF NOT EXISTS `item_table`
(
    item_id STRING COMMENT "Unique ID of the item"
    ,item_type STRING COMMENT "Type of the item"
    ,title STRING COMMENT "Item title"
    ,content STRING COMMENT "Body part of the item"
    ,pub_time STRING COMMENT "Release time"
    ,status STRING COMMENT "Whether the item can be recommended"
    ,expire_time STRING COMMENT "Time at which the item expires"
    ,last_modify_time STRING COMMENT "Last modification time of the item information"
    ,scene_id STRING COMMENT "Scene ID"
    ,duration STRING COMMENT "Duration, in seconds"
    ,category_level STRING COMMENT "Category level"
    ,category_path STRING COMMENT "Category path"
    ,tags STRING COMMENT "Tags"
    ,channel STRING COMMENT "Channels"
    ,organization STRING COMMENT "Organizations"
    ,author STRING COMMENT "Authors"
    ,pv_cnt STRING COMMENT "Number of exposures"
    ,click_cnt STRING COMMENT "Number of clicks"
    ,like_cnt STRING COMMENT "Number of likes"
    ,unlike_cnt STRING COMMENT "Number of dislikes"
    ,comment_cnt STRING COMMENT "Number of comments"
    ,collect_cnt STRING COMMENT "Number of favorites"
    ,share_cnt STRING COMMENT "Number of shares"
    ,download_cnt STRING COMMENT "Number of downloads"
    ,tip_cnt STRING COMMENT "Number of rewards"
    ,subscribe_cnt STRING COMMENT "Number of follows"
    ,source_id STRING COMMENT "Item source"
    ,country STRING COMMENT "Country"
    ,city STRING COMMENT "City"
    ,features STRING COMMENT "Additional characteristics"
    ,num_features STRING COMMENT "Additional characteristics, which are numerical values"
    ,weight STRING COMMENT "Weight of the item, default value: 1"
)
PARTITIONED BY
(
    ds STRING
)
LIFECYCLE 30
;