CN113392320A - Knowledge service-based satellite remote sensing service providing method - Google Patents
Knowledge service-based satellite remote sensing service providing method Download PDFInfo
- Publication number
- CN113392320A CN113392320A CN202110530182.3A CN202110530182A CN113392320A CN 113392320 A CN113392320 A CN 113392320A CN 202110530182 A CN202110530182 A CN 202110530182A CN 113392320 A CN113392320 A CN 113392320A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- user
- service
- remote sensing
- satellite remote
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a satellite remote sensing service providing method based on knowledge service, which is characterized in that satellite remote sensing data are fused to generate core knowledge, a knowledge agent is constructed on the basis of the core knowledge, and the knowledge agent classifies the satellite remote sensing data to construct a knowledge service platform; the analysis of the user is completed through a recommendation algorithm and a collaborative filtering algorithm based on the content; and the knowledge agent carries out corresponding analysis and adjustment according to the feedback of the user. The satellite remote sensing service providing method based on the knowledge service can convert the knowledge actively retrieved by people into the knowledge actively approaching the user, try to predict the requirement of the user on certain data through the label selected by the user, recommend the service possibly needed by the user, and adjust the strategy according to the behavior and feedback of the user to generate the recommendation result more conforming to the requirement of the user.
Description
Technical Field
The invention relates to the technical field of knowledge services, in particular to a satellite remote sensing service providing method based on knowledge services.
Background
The meteorological satellite career of China is developing at a high speed, and at present, the meteorological satellite can be used for monitoring disastrous and highly-influenced weather such as typhoon, rainstorm, strong convection, fog, sand dust, haze and the like, and surface environments such as flood water, forest and grassland fire, high temperature, drought and the like. The satellite ecological remote sensing service plays an outstanding role in ecological civilization construction.
Conventional data retrieval is usually performed actively by people, but the search purpose of many users in life is ambiguous. With the progress of artificial intelligence and the rise of recommendation systems in recent years, more and more scenes are converted from the way that people actively retrieve knowledge to the way that the knowledge is actively close to users. The recommendation system can present the user with items that he (or she) may be interested in, depending on the user's preferences and behaviors.
The recommendation system is an important tool for helping users to discover content and overcome information overload. The recommendation system belongs to an application of information filtering. The method models the interest of the user by analyzing the user behavior, and recommends information or objects which are possibly favored to the user. The recommendation system firstly collects historical behavior data of a user, then obtains a user evaluation matrix through a preprocessing method, and then forms personalized recommendation for the user by using related recommendation technologies in the field of machine learning. Some recommendation systems also collect feedback of the user on the recommendation result, and adjust the recommendation strategy in real time according to actual feedback information to generate a recommendation result more meeting the user requirement.
A satellite remote sensing service providing method capable of actively recommending knowledge to a user is not available in the prior art.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a method for providing a satellite remote sensing service based on a knowledge service, which can overcome the defects in the prior art.
In order to achieve the technical purpose, the technical scheme of the invention is realized as follows:
a satellite remote sensing service providing method based on knowledge service comprises the following steps:
s1, fusing the satellite remote sensing data to generate core knowledge, and constructing a knowledge intelligent body on the basis of the core knowledge, wherein the knowledge intelligent body has a function of actively recommending the knowledge to a user, can be understood that the knowledge actively retrieved by a person is converted into an actively knowledge retriever, and classifies the satellite remote sensing data to construct a knowledge service platform so as to help the user to select services in the future;
s2, in the cold start stage, the analysis of the user is completed through the recommendation algorithm based on the content and the collaborative filtering algorithm;
and S3, the knowledge agent carries out corresponding analysis and adjustment according to the user feedback (the user behavior).
Further, in step S1, classifying the satellite remote sensing data into a database for performing unified management on the satellite remote sensing data, extracting attributes of the remote sensing data, classifying the remote sensing data according to different regions and different time periods, and building a knowledge network to provide knowledge content or a solution for the problem provided by the user.
Further, in the content-based recommendation algorithm in step S2, a recommendation algorithm model is constructed based on the object-related information, the user-related information, and the user' S operation behavior on the object, so as to provide a recommendation service for the user. Firstly, recommending according to the label and the attribute of the user, for example, recommending data of corresponding time of a corresponding region for the user according to the region where the user is located and the working time of frequent online; and predicting the content which is possibly needed by the user according to the content searched by the user, and recommending the content which is similar to the content searched by the user in the past.
Further, the collaborative filtering algorithm in step S2 is to calculate the similarity between users according to the historical behavior information of users and some attributes, set a similarity threshold, obtain the nearest neighbor of the target user according to the similarity between users, sort the similarity, and predict the service that the user may need by using the nearest neighbor of the target user by using the nearest neighbor technology. And meanwhile, collaborative filtering recommendation can be performed according to similar user behaviors in the same region.
Further, the algorithm for calculating the similarity may be implemented by a cosine algorithm.
Further, in step S3, the analyzing and adjusting according to the user feedback is to adopt the Rocchi algorithm to process the user feedback, modify the query vector value of the user, and perform corresponding recommendation adjustment.
Further, the user feedback includes the number of clicks on a certain content, the residence time on a certain page, the browsing number of a certain page, and the collection behavior.
The invention has the beneficial effects that: the method for providing the satellite remote sensing service based on the knowledge service generates core knowledge by fusing the satellite remote sensing data, constructs a knowledge intelligent body on the basis of the core knowledge, classifies the satellite remote sensing data by the knowledge intelligent body, constructs a knowledge service platform, converts the actively retrieved knowledge into the knowledge actively approaching to a user, tries to predict the requirement of the user on certain data by a label selected by the user, recommends the service possibly required by the user, and adjusts the strategy according to the behavior and feedback of the user to generate a recommendation result more conforming to the requirement of the user.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
The method for providing the satellite remote sensing service based on the knowledge service comprises the following steps:
s1, fusing the satellite remote sensing data to generate core knowledge, and constructing a knowledge intelligent body on the basis of the core knowledge, wherein the knowledge intelligent body has a function of actively recommending the knowledge to a user, can be understood that the knowledge actively retrieved by a person is converted into an actively knowledge retriever, and classifies the satellite remote sensing data to construct a knowledge service platform so as to help the user to select services in the future;
s2, in the cold start stage, the analysis of the user is completed through the recommendation algorithm based on the content and the collaborative filtering algorithm;
and S3, the knowledge agent carries out corresponding analysis and adjustment according to the user feedback (the user behavior).
In step S1, the classification of the satellite remote sensing data is performed by uniformly managing the satellite remote sensing data using a database, extracting attributes of the remote sensing data, classifying the remote sensing data according to different regions and different time periods, and building a knowledge network to provide knowledge content or solutions for the problems provided by users.
In the step S2, the content-based recommendation algorithm is to construct a recommendation algorithm model based on the object-related information, the user-related information, and the operation behavior of the user on the object, so as to provide a recommendation service for the user. Firstly, recommending according to the label and the attribute of the user, for example, recommending data of corresponding time of a corresponding region for the user according to the region where the user is located and the working time of frequent online; predicting the content which is possibly needed by the user according to the content searched by the user, and recommending the content which is similar to the past search preference of the user; the collaborative filtering algorithm is used for calculating the similarity between users according to the historical behavior information of the users and some attributes, setting a similarity threshold value, obtaining the nearest neighbor of a target user according to the similarity between the users, sequencing the similarity, and predicting the service possibly required by the users by using the nearest neighbor of the target user by adopting the nearest neighbor technology. And meanwhile, collaborative filtering recommendation can be performed according to similar user behaviors in the same region. The algorithm for calculating the similarity can be implemented by a cosine algorithm.
In step S3, the analyzing and adjusting according to the user feedback is to adopt a Rocchi algorithm to process the user feedback, modify the query vector value of the user, and perform corresponding recommendation adjustment; the user feedback comprises the number of clicks on a certain content, the residence time on a certain page, the browsing times on a certain page and the collection behavior.
For the convenience of understanding the above technical solutions of the present invention, the following detailed description will be given by way of examples.
(1) Integrating data
Firstly, the knowledge agent classifies the satellite remote sensing data according to different regions and time periods to construct a knowledge service platform. In order to later assist the user in making the selection of the service.
The satellite remote sensing data can be classified as shown in table 1:
TABLE 1 satellite remote sensing data
(2) User analysis
Suppose that the positioning information of the user A is a Beijing Hai lake area, the login time is generally 10:00 and 18:00, and keywords such as 'temperature', 'rain', 'snow' and the like are searched. The user B is located in the area facing the sun in Beijing, the login time is generally 9:00, keywords such as 'raining' and 'humidity' are searched once, and the precipitation of the Beijing is inquired at 9:30 of the day.
When the user A logs in the platform system, the knowledge agent actively pushes the first page of data such as precipitation and cloud water, temperature profile, wind profile, humidity profile and ozone profile of Beijing 9:00-12:00 and 17:00-20: 00. Meanwhile, the user B is locked as the most similar user through a cosine algorithm of collaborative filtering, and the data of 'precipitation and cloud water' which are most needed by the user A are predicted. And finally, the precipitation and cloud water data of about 10:00 are placed at the head of the push page.
(3) Feedback adjustment
If the user clicks the data of 'precipitation and cloud water' and 'humidity profile' in the page in the process of browsing the page, but the dwell time of the data of the 'humidity profile' on the page is long, and the knowledge intelligence body can put the data of the 'humidity profile' on the top page after refreshing.
In summary, by means of the above technical solution of the present invention, the knowledge service firstly fuses the satellite remote sensing data to generate core knowledge, and in addition to the core knowledge, a knowledge agent is constructed, which has a function of actively searching for users, and the people actively search knowledge and convert the knowledge into knowledge actively searching people; and constructing a knowledge service platform, wherein after a user logs in the system, knowledge can be automatically gathered for the user, the platform system can try to predict the requirement of the user on certain data through a label selected by the user so as to recommend services possibly required by the user, and a recommendation result more conforming to the requirement of the user is generated by adjusting a strategy according to the behavior and feedback of the user.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A satellite remote sensing service providing method based on knowledge service is characterized by comprising the following steps:
s1, fusing the satellite remote sensing data to generate core knowledge, and constructing a knowledge agent on the basis of the core knowledge, wherein the knowledge agent classifies the satellite remote sensing data to construct a knowledge service platform;
s2, the analysis of the user is completed through the recommendation algorithm based on the content and the collaborative filtering algorithm;
and S3, the knowledge agent analyzes and adjusts accordingly according to the feedback of the user.
2. The method for providing satellite remote sensing service based on knowledge service as claimed in claim 1, wherein the step S1 classifies the satellite remote sensing data into remote sensing data classified according to different regions and different time periods.
3. The method for providing satellite remote sensing service based on knowledge service as claimed in claim 1, wherein the content-based recommendation algorithm in step S2 is to construct a recommendation algorithm model based on the object-related information, the user-related information and the user' S operation behavior on the object, so as to provide recommendation service to the user.
4. The method for providing satellite remote sensing service based on knowledge service according to claim 1, wherein the collaborative filtering algorithm in step S2 is to calculate similarity between users according to historical behavior information and attributes of the users, set a similarity threshold, obtain nearest neighbors of target users according to the similarity between the users, sort the similarity, and predict services that the users may need by using the nearest neighbors of the target users.
5. The knowledge-based service satellite remote sensing service providing method according to claim 4, wherein an algorithm for calculating the similarity is a cosine algorithm.
6. The method for providing satellite remote sensing service based on knowledge service according to claim 1, wherein the analyzing and adjusting according to the user feedback in step S3 is to process the user feedback by Rocchi algorithm, modify the query vector value of the user, and perform corresponding recommendation adjustment.
7. The method for providing satellite remote sensing service based on knowledge service as claimed in claim 6, wherein the user feedback comprises click times of certain content, residence time on certain page, browsing times of certain page, and collecting behavior.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110530182.3A CN113392320A (en) | 2021-05-14 | 2021-05-14 | Knowledge service-based satellite remote sensing service providing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110530182.3A CN113392320A (en) | 2021-05-14 | 2021-05-14 | Knowledge service-based satellite remote sensing service providing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113392320A true CN113392320A (en) | 2021-09-14 |
Family
ID=77617151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110530182.3A Pending CN113392320A (en) | 2021-05-14 | 2021-05-14 | Knowledge service-based satellite remote sensing service providing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392320A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391670A (en) * | 2017-07-21 | 2017-11-24 | 云南电网有限责任公司教育培训评价中心 | A kind of mixing recommendation method for merging collaborative filtering and user property filtering |
| CN111666313A (en) * | 2020-05-25 | 2020-09-15 | 中科星图股份有限公司 | Correlation construction and multi-user data matching method based on multi-source heterogeneous remote sensing data |
| CN112685571A (en) * | 2020-12-28 | 2021-04-20 | 中国南方电网有限责任公司超高压输电公司 | Knowledge graph generation recommendation system based on big data |
-
2021
- 2021-05-14 CN CN202110530182.3A patent/CN113392320A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391670A (en) * | 2017-07-21 | 2017-11-24 | 云南电网有限责任公司教育培训评价中心 | A kind of mixing recommendation method for merging collaborative filtering and user property filtering |
| CN111666313A (en) * | 2020-05-25 | 2020-09-15 | 中科星图股份有限公司 | Correlation construction and multi-user data matching method based on multi-source heterogeneous remote sensing data |
| CN112685571A (en) * | 2020-12-28 | 2021-04-20 | 中国南方电网有限责任公司超高压输电公司 | Knowledge graph generation recommendation system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Topic based context-aware travel recommendation method exploiting geotagged photos | |
| CN110430471B (en) | Television recommendation method and system based on instantaneous calculation | |
| Yang et al. | Region based image annotation through multiple-instance learning | |
| CN110163647B (en) | Data processing method and device | |
| CN111191122A (en) | Learning resource recommendation system based on user portrait | |
| CN111382361B (en) | Information pushing method, device, storage medium and computer equipment | |
| CN113159826B (en) | Garment fashion element prediction system and method based on deep learning | |
| CN108846097B (en) | User interest tag representation method, article recommendation device and equipment | |
| CN103235823A (en) | Method and system for determining current interest of users according to related web pages and current behaviors | |
| CN112269882A (en) | Tourist attraction recommendation method oriented to knowledge map | |
| CN109189943B (en) | Method for extracting capability knowledge and constructing capability knowledge map | |
| CN108230007A (en) | A kind of recognition methods of user view, device, electronic equipment and storage medium | |
| CN110019616A (en) | A kind of POI trend of the times state acquiring method and its equipment, storage medium, server | |
| CN109408578A (en) | One kind being directed to isomerous environment monitoring data fusion method | |
| CN111538751B (en) | Tagged user portrait generation system and method for Internet of things data | |
| CN115048586B (en) | Multi-feature-fused news recommendation method and system | |
| CN110232133A (en) | A kind of image of clothing search method and system classified based on Fusion Features and style | |
| CN111143689A (en) | Method for constructing recommendation engine according to user requirements and user portrait | |
| CN111159559A (en) | Method for constructing recommendation engine according to user requirements and user behaviors | |
| Zheng | Multi level recommendation system of college online learning resources based on multi intelligence algorithm | |
| CN112765374A (en) | Education resource screening system and method for information push | |
| CN113392320A (en) | Knowledge service-based satellite remote sensing service providing method | |
| Zheng et al. | Personalized tag recommendation based on convolution feature and weighted random walk | |
| Zhang | Remote sensing data processing of urban land using based on artificial neural network | |
| Silva et al. | USTAR: Online multimodal embedding for modeling user-guided spatiotemporal activity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |