Recommendation method and recommendation system based on big data analysis and cloud platform
By obtaining user behavior, characteristics and environment data, determining recommendation preference types and formulating corresponding strategies, and dynamically adjusting recommendation content, the problem that the existing recommendation system cannot adapt to users' personalized needs is solved, and recommendation results that are more in line with user needs are achieved.
Patent Information
- Application Number
- CN202411436216.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing recommendation system cannot effectively adapt to users' personalized needs, and the fixed recommendation strategy cannot meet the needs of users' diverse preferences, especially in front of different users, which cannot dynamically adjust the recommended content.
By obtaining user behavioral data, characteristic data and environmental data, determine the user's recommendation preference type, formulate corresponding recommendation strategies, and dynamically adjust the recommended content, such as recommending content with high similarity for conservative users and recommending novelty for radical users Higher content.
It realizes dynamic adjustment of recommended content based on user real-time behavior and environmental data, so that the recommendation results are more in line with the changes in users' current needs and preferences, and meet the diverse needs of users.
Smart Images

Figure CN118939882A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data technology, and in particular to a recommendation method and a recommendation system based on big data analysis and a cloud platform. Background Art
[0002] With the rapid development of the Internet and the continuous accumulation of user behavior data, personalized recommendation systems have played a vital role in e-commerce, video, music and other platforms. Recommendation systems in existing technologies usually make recommendations based on user behavior data (such as search, click, favorite, and comment, etc.), and recommend content or products that match the user's interests by analyzing the user's historical behavior and preferences. However, with the surge in data volume and the diversification of user needs, traditional recommendation methods have gradually exposed some shortcomings and limitations.
[0003] Existing recommendation systems often rely on fixed recommendation algorithms or models, such as collaborative filtering or content-based recommendations. These methods usually assume that all users have similar preferences and recommend similar content to all users. However, user needs and preferences are diverse, especially when facing different users, fixed recommendation strategies cannot adapt to their personalized needs.
[0004] Therefore, there is an urgent need for a recommendation method and a recommendation system that can formulate different recommendation strategies according to different user preferences. Summary of the invention
[0005] The present invention provides a recommendation method based on big data analysis and cloud platform, comprising: Acquiring user data, wherein the user data includes feature data, behavior data and environment data; Determine a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended, and radical; Obtain historical recommendation data stored in the cloud platform; Determining a recommendation strategy based on the historical recommendation data and the recommendation preference type; A recommendation sequence is determined based on the recommendation strategy and the user data.
[0006] Further, determining the recommendation preference type based on the user data includes: Based on the behavioral data, determining a basic preference attribute; Based on the feature data, determining basic portrait attributes; Based on the environmental data, determining an environmental trend attribute; The recommendation preference type is determined based on the basic preference attribute, the basic portrait attribute and the environmental trend attribute.
[0007] Furthermore, the behavior data includes search data, click data, favorite data and comment data; The determining of basic preference attributes based on the behavior data includes: Determine the content search percentage based on the search data; Determine the content click ratio based on the click data; Determine the content collection ratio based on the collection data; Based on the comment data, determining a user sentiment trend vector; Determine a basic preference score based on the content search ratio, the content click ratio, the content collection ratio and the user sentiment trend vector; If the basic preference score is less than or equal to a first threshold, determining that the basic preference attribute is a conservative attribute; If the basic preference score is less than or equal to a second threshold, determining that the basic preference attribute is an extended attribute; If the basic preference score is greater than the second threshold, the basic preference attribute is determined to be an aggressive attribute.
[0008] Furthermore, the characteristic data includes identity data and social data, the identity data includes age, gender and occupation type, and the social data includes the number of friends and interaction frequency; The determining of basic portrait attributes based on the feature data includes: Based on the gender and the occupation type, according to the preset classification attributes, determine the gender meta-value and the occupation meta-value respectively; Construct a feature matrix based on the target user's associated age, gender meta-value, occupation meta-value, number of friends, and interaction frequency; Determine a user score based on the feature matrix and the weight matrix; If the user score is greater than or equal to the score threshold, determining that the basic portrait attribute is a positive bias attribute; If the user score is less than the score threshold, the basic portrait attribute is determined to be a negatively biased attribute.
[0009] Further, the environmental data includes active location and active time; The determining of the environmental trend attribute based on the environmental data includes: Determining whether the active time is within a preset time interval and whether the active location is within a preset location range; If both are true, then the environmental trend attribute is determined to be a positive trend; Otherwise, it is determined that the environmental trend attribute is a negative trend.
[0010] Furthermore, determining the recommendation preference type based on the basic preference attribute, the basic portrait attribute and the environmental trend attribute includes: In response to the basic preference attribute being a conservative attribute, If the basic image attribute is a negative bias attribute and / or the environmental trend attribute is a negative trend, the recommendation preference type is determined to be conservative; otherwise, the recommendation preference type is determined to be extended; In response to the basic preference attribute being an extended attribute, If the basic image attribute is a positive bias attribute and the environmental trend attribute is a positive trend, the recommendation preference type is determined to be radical; otherwise, the recommendation preference type is determined to be extended; In response to the basic preference attribute being an aggressive attribute, If the basic portrait attribute is a positive bias attribute and / or the environmental trend attribute is a positive trend, the recommended preference type is determined to be radical; otherwise, the recommended preference type is determined to be extended.
[0011] Further, based on the comment data, determining the user sentiment trend vector includes: The comment text is obtained, and the user emotion trend vector is generated according to the pre-trained emotion classification model.
[0012] Furthermore, the historical recommendation data includes type data, duration data and language attribute data; Determining a recommendation strategy based on the historical recommendation data and the recommendation preference type includes: Based on the type data, determine a type proportion set; Based on the duration data, determine a duration proportion set; Based on the language attribute data, determining a language proportion set; Based on the recommendation preference type, determining the preference weight; Based on the type proportion set, duration proportion set, language proportion set and preference proportion weights, the recommended type, recommended duration and recommended language attributes and their corresponding weight ratios are determined.
[0013] Further, determining a recommendation sequence based on the recommendation strategy and the user data includes: Determining, according to the weight ratio, the recommendation priorities corresponding to the recommendation type, the recommendation duration, and the recommended language attribute respectively; A recommendation sequence is determined according to the recommendation priority and the user data.
[0014] The present invention also provides a recommendation system based on big data analysis and cloud platform, comprising: An acquisition module is used to acquire user data, wherein the user data includes feature data, behavior data and environment data; and is also used to acquire historical recommendation data stored in the cloud platform; A type determination module, used to determine a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended and radical types; The recommendation module is used to determine a recommendation strategy based on the historical recommendation data and the recommendation preference type; and is also used to determine a recommendation sequence based on the recommendation strategy and the user data.
[0015] Compared with the prior art, the recommendation method and system based on big data analysis and cloud platform provided by the present invention have at least the following beneficial effects: This recommendation method based on big data analysis and cloud platform can obtain user behavior data, feature data and environmental data, and then comprehensively analyze user preferences, so as to accurately identify the user's recommendation preference type and formulate corresponding recommendation strategies based on the type. For example, for conservative users, content with high similarity to historical data is recommended; for radical users, novel content with low similarity is recommended, so as to better meet the diverse needs of users. This method can dynamically adjust the recommended content based on the user's real-time behavior and environmental data, so that the recommendation results are more in line with the user's current needs and preference changes. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 It is a flowchart of a recommendation system based on big data analysis and cloud platform according to some embodiments of this specification; Figure 2 It is a structural block diagram of a recommendation system based on big data analysis and cloud platform according to some embodiments of this specification; Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.
[0017] Figure number: 300-computer system; 301-CPU; 302-ROM; 303-RAM; 304-bus; 305-I / O interface; 306-input part; 307-output part; 308-storage part; 309-communication part; 310-drive; 311-removable medium. DETAILED DESCRIPTION
[0018] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
[0019] Figure 1 is a flow chart of a recommendation system based on big data analysis and cloud platform according to some embodiments of this specification, such as Figure 1 As shown, a recommendation method based on big data analysis and cloud platform may include the following steps. Each step is described in detail below.
[0020] Step S100, obtaining user data, wherein the user data includes feature data, behavior data and environment data.
[0021] It is worth noting that the behavioral data may include search data, click data, collection data and comment data; feature data may include identity data and social data, the identity data includes age, gender and occupation type, and the social data includes the number of friends and interaction frequency; environmental data may include active locations and active times. Specifically, search data refers to the search query records of users on the platform. This type of data can reveal the user's interest and demand for certain content. For example, users who frequently search for "technology news" may indicate that they are interested in technology-related content. Click data refers to the content or links that users have clicked on. This type of data provides the user's interest level and priority in specific content. Collection data refers to the list of content collected by users. This type of data represents the user's long-term interest and value assessment of certain content. Comment data refers to the user's comments on the content, including comment text and ratings. Active locations and active times can evaluate the environment in which the user is active, and then judge the user's preference needs.
[0022] Step S200: determining a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended, and radical.
[0023] Specifically, the basic preference attributes can be determined based on the behavioral data; the basic portrait attributes can be determined based on the feature data; the environmental trend attributes can be determined based on the environmental data; and the recommended preference type can be determined based on the basic preference attributes, the basic portrait attributes and the environmental trend attributes.
[0024] In this embodiment, determining the basic preference type based on the behavior data includes: determining the content search ratio based on the search data; determining the content click ratio based on the click data; determining the content collection ratio based on the collection data; determining the user emotion trend vector based on the comment data; determining the basic preference score based on the content search ratio, the content click ratio, the content collection ratio and the user emotion trend vector; if the basic preference score is less than or equal to a first threshold, determining that the basic preference attribute is a conservative attribute; if the basic preference score is less than or equal to a second threshold, determining that the basic preference attribute is an extended attribute; if the basic preference score is greater than the second threshold, determining that the basic preference attribute is an aggressive attribute.
[0025] Specifically, based on the content search proportion, the content click proportion, the content collection proportion and the user sentiment trend vector, the basic preference score is determined, which can be calculated using the following formula:
[0026] in, As the basic preference score, is the user sentiment trend vector, a, b, and c are the content search proportion, the content click proportion, and the content collection proportion, respectively.
[0027] It is worth noting that this method not only relies on single behavioral data, but also integrates multi-dimensional data (such as search, click, favorite, comment), and combines sentiment analysis technology to determine the user's emotional trend, thereby more comprehensively capturing the user's preferences and avoiding the recommendation content bias caused by relying only on a single behavioral dimension. At the same time, by regularly analyzing the user's behavioral data and updating their preference scores in real time, the recommendation system can adapt to changes in user needs in a timely manner. By converting behavioral data into user preference scores and then classifying users based on preset thresholds, the recommendation decision process can be effectively simplified and complex calculation processes can be avoided.
[0028] It is also worth noting that determining the user emotion trend vector based on the comment data includes: obtaining the comment text, and generating the user emotion trend vector according to a pre-trained emotion classification model.
[0029] In this embodiment, the basic portrait attributes are determined based on the feature data, including: based on the gender and the occupation type, according to preset classification attributes, the gender meta-value and the occupation meta-value are determined respectively; based on the age, gender meta-value, occupation meta-value, number of friends and interaction frequency associated with the target user, a feature matrix is constructed; based on the feature matrix and the weight matrix, the user score is determined; if the user score is greater than or equal to a score threshold, the basic portrait attribute is determined to be a positive biased attribute; if the user score is less than the score threshold, the basic portrait attribute is determined to be a negative biased attribute.
[0030] It is worth noting that age can be a numeric type; gender is a binary value, 0 for male and 1 for female; occupation type can be represented by multiple categories, such as technical = 1, literary = 2, etc. The number of friends and interaction frequency can also be numeric types. Specifically, based on the age, gender meta-value, occupation meta-value, number of friends and interaction frequency associated with the target user, the feature matrix can be constructed. For example, user A is 28 years old, male (the corresponding gender meta-value is 0), technical (the corresponding gender meta-value is 1), the number of friends is 450, and the interaction frequency is 30 times; then the corresponding feature matrix can be constructed as [28 0 1 450 30]. Correspondingly, by collecting the remaining user information, a multi-source feature matrix can be obtained, such as the feature matrix:
[0031] It is also worth noting that the weight matrix can be [0.4 0.2 0.2 0.01 0.19], which respectively corresponds to the importance of age, gender meta-value, occupation meta-value, number of friends and interaction frequency. By multiplying the feature matrix by the weight matrix, a user score can be obtained.
[0032] In this embodiment, the environmental data includes active locations and active times; determining the environmental trend attribute based on the environmental data includes: judging whether the active time is within a preset time interval and whether the active location is within a preset location range; if both are true, determining that the environmental trend attribute is a positive trend; otherwise, determining that the environmental trend attribute is a negative trend.
[0033] In this embodiment, the determination of the recommendation preference type based on the basic preference attribute, the basic portrait attribute and the environmental trend attribute includes: in response to the basic preference attribute being a conservative attribute, if the basic portrait attribute is a negative bias attribute and / or the environmental trend attribute is a negative trend, determining the recommendation preference type to be conservative; otherwise, determining the recommendation preference type to be extended; in response to the basic preference attribute being an extended attribute, if the basic portrait attribute is a positive bias attribute and the environmental trend attribute is a positive trend, determining the recommendation preference type to be radical; otherwise, determining the recommendation preference type to be extended; in response to the basic preference attribute being an radical attribute, if the basic portrait attribute is a positive bias attribute and / or the environmental trend attribute is a positive trend, determining the recommendation preference type to be radical; otherwise, determining the recommendation preference type to be extended.
[0034] Step S300, obtaining historical recommendation data stored in the cloud platform; Step S400: determining a recommendation strategy based on the historical recommendation data and the recommendation preference type.
[0035] Among them, the historical recommendation data includes type data, duration data and language attribute data; based on the historical recommendation data and the recommendation preference type, a recommendation strategy is determined, including: based on the type data, determining a type proportion set; based on the duration data, determining a duration proportion set; based on the language attribute data, determining a language proportion set; based on the recommendation preference type, determining a preference proportion weight; based on the type proportion set, duration proportion set, language proportion set and preference proportion weight, determining the recommended type, recommended duration and recommended language attribute and their corresponding weight ratios.
[0036] Step S500: determining a recommendation sequence based on the recommendation strategy and the user data.
[0037] Specifically, determining the recommendation sequence based on the recommendation strategy and the user data includes: determining the recommendation priorities corresponding to the recommendation type, the recommendation duration and the recommended language attribute respectively according to the weight ratio; and determining the recommendation sequence according to the recommendation priorities and the user data.
[0038] Figure 2 is a structural block diagram of a recommendation system based on big data analysis and cloud platform according to some embodiments of this specification, such as Figure 2As shown, a recommendation system based on big data analysis and cloud platform may include: an acquisition module for acquiring user data, wherein the user data includes feature data, behavior data and environment data; and also for acquiring historical recommendation data stored in the cloud platform; a type determination module for determining a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended and radical; a recommendation module for determining a recommendation strategy based on the historical recommendation data and the recommendation preference type; and also for determining a recommendation sequence based on the recommendation strategy and the user data. A recommendation system based on big data analysis and cloud platform may apply a recommendation method based on big data analysis and cloud platform. For more descriptions of a recommendation system based on big data analysis and cloud platform, please refer to the relevant descriptions of a recommendation method based on big data analysis and cloud platform, which will not be repeated here.
[0039] Figure 3 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 3 The computer system 300 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0040] like Figure 3 As shown, the computer system 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.
[0041] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0042] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.
[0043] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable computer program. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0044] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0045] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0046] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor of a computer, the computer executes the above method. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.
[0047] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the recommendation method based on big data analysis and cloud platform provided in each of the above embodiments.
[0048] The above embodiments are only preferred embodiments for fully illustrating the present application, and the protection scope of the present application is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present application is within the protection scope of the present application.
Claims
1. A recommendation method based on big data analysis and cloud platform, characterized in that: include: Acquiring user data, wherein the user data includes feature data, behavior data and environment data; Determine a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended, and radical; Obtain historical recommendation data stored in the cloud platform; Determining a recommendation strategy based on the historical recommendation data and the recommendation preference type; A recommendation sequence is determined based on the recommendation strategy and the user data.
2. The recommendation method based on big data analysis and cloud platform according to claim 1, characterized in that: The determining the recommendation preference type based on the user data includes: Based on the behavioral data, determining a basic preference attribute; Based on the feature data, determining basic portrait attributes; Based on the environmental data, determining an environmental trend attribute; The recommendation preference type is determined based on the basic preference attribute, the basic portrait attribute and the environmental trend attribute.
3. The recommendation method based on big data analysis and cloud platform according to claim 2, characterized in that: The behavior data includes search data, click data, favorite data and comment data; The determining of basic preference attributes based on the behavior data includes: Determine the content search percentage based on the search data; Determine the content click ratio based on the click data; Determine the content collection ratio based on the collection data; Based on the comment data, determining a user sentiment trend vector; Determine a basic preference score based on the content search ratio, the content click ratio, the content collection ratio and the user sentiment trend vector; If the basic preference score is less than or equal to a first threshold, determining that the basic preference attribute is a conservative attribute; If the basic preference score is less than or equal to a second threshold, determining that the basic preference attribute is an extended attribute; If the basic preference score is greater than the second threshold, the basic preference attribute is determined to be an aggressive attribute.
4. The recommendation method based on big data analysis and cloud platform according to claim 3, characterized in that: The characteristic data includes identity data and social data. The identity data includes age, gender and occupation type. The social data includes the number of friends and interaction frequency. The determining of basic portrait attributes based on the feature data includes: Based on the gender and the occupation type, according to the preset classification attributes, determine the gender meta-value and the occupation meta-value respectively; Construct a feature matrix based on the target user's associated age, gender meta-value, occupation meta-value, number of friends, and interaction frequency; Determine a user score based on the feature matrix and the weight matrix; If the user score is greater than or equal to the score threshold, determining that the basic portrait attribute is a positive bias attribute; If the user score is less than the score threshold, the basic portrait attribute is determined to be a negatively biased attribute.
5. The recommendation method based on big data analysis and cloud platform according to claim 4, characterized in that: The environmental data includes active location and active time; The determining of the environmental trend attribute based on the environmental data includes: Determining whether the active time is within a preset time interval and whether the active location is within a preset location range; If both are true, then the environmental trend attribute is determined to be a positive trend; Otherwise, it is determined that the environmental trend attribute is a negative trend.
6. The recommendation method based on big data analysis and cloud platform according to claim 5, characterized in that: The determining the recommendation preference type based on the basic preference attribute, the basic portrait attribute and the environmental trend attribute includes: In response to the basic preference attribute being a conservative attribute, If the basic image attribute is a negative bias attribute and / or the environmental trend attribute is a negative trend, the recommendation preference type is determined to be conservative; otherwise, the recommendation preference type is determined to be extended; In response to the basic preference attribute being an extended attribute, If the basic image attribute is a positive bias attribute and the environmental trend attribute is a positive trend, the recommendation preference type is determined to be radical; otherwise, the recommendation preference type is determined to be extended; In response to the basic preference attribute being an aggressive attribute, If the basic portrait attribute is a positive bias attribute and / or the environmental trend attribute is a positive trend, the recommended preference type is determined to be radical; otherwise, the recommended preference type is determined to be extended.
7. The recommendation method based on big data analysis and cloud platform according to claim 3, characterized in that: Based on the comment data, determining a user sentiment trend vector includes: The comment text is obtained, and the user emotion trend vector is generated according to the pre-trained emotion classification model.
8. The recommendation method based on big data analysis and cloud platform according to claim 1, characterized in that: The historical recommendation data includes type data, duration data and language attribute data; Determining a recommendation strategy based on the historical recommendation data and the recommendation preference type includes: Based on the type data, determine a type proportion set; Based on the duration data, determine a duration proportion set; Based on the language attribute data, determining a language proportion set; Based on the recommendation preference type, determining the preference weight; Based on the type proportion set, duration proportion set, language proportion set and preference proportion weights, the recommended type, recommended duration and recommended language attributes and their corresponding weight ratios are determined.
9. The recommendation method based on big data analysis and cloud platform according to claim 8, characterized in that: The determining of the recommendation sequence based on the recommendation strategy and the user data includes: Determining, according to the weight ratio, the recommendation priorities corresponding to the recommendation type, the recommendation duration, and the recommended language attribute respectively; A recommendation sequence is determined according to the recommendation priority and the user data.
10. A recommendation system based on big data analysis and cloud platform, characterized in that: include An acquisition module is used to acquire user data, wherein the user data includes feature data, behavior data and environment data; and is also used to acquire historical recommendation data stored in the cloud platform; A type determination module, used to determine a recommendation preference type based on the user data, wherein the recommendation preference type includes conservative, extended and radical types; The recommendation module is used to determine a recommendation strategy based on the historical recommendation data and the recommendation preference type; and is also used to determine a recommendation sequence based on the recommendation strategy and the user data.
Citation Information
Patent Citations
Object recommendation method and device, storage medium, processor and system
CN110020102A
Content recommendation method and device based on artificial intelligence
CN114741423A
Content recommendation system based on artificial intelligence, electronic equipment and storage medium
CN117972206A
Cited By
Commodity recommendation method and system based on artificial intelligence
CN120634660A
AI recommendation order placing method and system and electronic equipment
CN120672415A
An AI recommendation ordering method, system and electronic device
CN120672415B
