CN113076485B

CN113076485B - Resource recommendation method, device, equipment and storage medium based on intelligent degradation

Info

Publication number: CN113076485B
Application number: CN202110465409.0A
Authority: CN
Inventors: 乐志能
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Filing date: 2021-04-28
Publication date: 2024-06-28
Anticipated expiration: 2041-04-28

Abstract

The invention relates to a data analysis technology, and discloses a resource recommendation method based on intelligent degradation, which comprises the following steps: extracting an access identifier of a resource recommendation request; if the access identifier is the first identifier, generating a resource recommendation list according to a first strategy to recommend the user, and storing the resource recommendation list and the user in an associated manner; if the access identifier is the second identifier, acquiring the user characteristics and the target degradation characteristics; judging whether the user characteristic is in the target degradation characteristic or not; if not, generating a resource recommendation list according to a first strategy to recommend the user, and storing the resource recommendation list and the user in a correlated way; and if yes, calling the stored resource recommendation list to recommend the user. In addition, the invention also relates to a blockchain technology, and the user characteristics can be stored in nodes of the blockchain. The invention further provides a resource recommendation device, equipment and medium based on intelligent degradation. The invention can solve the problem that the computing resource is empty when the recommended service of the user is degraded.

Description

Resource recommendation method, device, equipment and storage medium based on intelligent degradation

Technical Field

The present invention relates to the field of data analysis technologies, and in particular, to a resource recommendation method and apparatus based on intelligent degradation, an electronic device, and a computer readable storage medium.

Background

When recommending resources for users, a unified server often analyzes user data, and generates a recommendation list conforming to the users according to analysis results so as to realize intelligent recommendation for the users. However, when the number of concurrent users is too large, or the server has a partial failure, the amount of user data that can be analyzed by the server is partially reduced, so that the recommendation of the users needs to be degraded, for example, the accurate recommendation for each user is degraded to a unified template recommendation for a certain type of user group.

At present, the solution that the server cannot normally provide the recommended service is mainly to carry out indiscriminate degradation on all users, but the server is often only partially reduced in function, if the recommended service of the resources of all users is directly degraded, a large amount of computing resources of the server are left empty, so that the problem of how to realize intelligent degradation on the recommended service of the resources when the server cannot normally provide the recommended service is urgent to be solved.

Disclosure of Invention

The invention provides a resource recommendation method and device based on intelligent degradation and a computer readable storage medium, and mainly aims to solve the problem that computing resources are empty when a recommended service of a user is degraded.

In order to achieve the above object, the present invention provides a resource recommendation method based on intelligent degradation, including:

Acquiring a resource recommendation request of a user, and extracting an access identifier in the resource recommendation request;

if the access identifier is a first identifier, determining that the resource recommendation request is a first request, generating a resource recommendation list according to a first strategy, recommending resources to the user, and storing the resource recommendation list and the user in an associated mode;

if the access identifier is a second identifier, determining that the resource recommendation request is a non-first request, and acquiring a pre-stored user characteristic and a target degradation characteristic;

Judging whether the user characteristic is in a target degradation characteristic or not;

If the user characteristics are not in the target degradation characteristics, generating a resource recommendation list according to the first strategy to recommend resources to the user, and storing the resource recommendation list and the user in an associated mode;

And if the user characteristics are in the target degradation characteristics, calling a resource recommendation list stored in association with the user to recommend resources to the user.

Optionally, the extracting the access identifier in the resource recommendation request includes:

traversing the resource recommendation request to determine the position of a field interval symbol in the resource recommendation request;

dividing the resource recommendation request into a plurality of request fields according to the positions of the field interval symbols, and numbering the plurality of request fields in the sequence from front to back in the resource recommendation request;

selecting a request field with a preset number, and analyzing the selected request field to obtain a request identifier.

Optionally, the generating a resource recommendation list according to the first policy performs resource recommendation on the user, including:

acquiring user data of the user, and generating a user portrait of the user according to the user data;

Acquiring a plurality of resources to be recommended, and respectively carrying out matching analysis on the plurality of resources to be recommended and the user portrait to obtain the matching degree of each resource to be recommended and the user portrait;

Selecting resources to be recommended, the matching degree of which is greater than a preset matching degree threshold value, and sequencing the selected resources to be recommended according to the sequence of the matching degree from large to small to generate a resource recommendation list;

and recommending the resources to the user according to the resource recommendation list.

Optionally, the generating the user portrait of the user according to the user data includes:

performing text conversion on the user data to obtain text data;

Word segmentation processing is carried out on the text data to obtain text word segmentation;

word vector conversion is carried out on the text word segmentation to obtain text word vectors;

extracting features of the text word vector by using a pre-trained feature extraction algorithm to obtain a feature word vector;

And generating a user portrait of the user according to the feature word vector.

Optionally, the word segmentation processing is performed on the text data to obtain text word segmentation, including:

obtaining a pre-built standard dictionary, wherein the standard dictionary comprises a plurality of standard word segmentation;

Dividing the text data into texts according to a preset first length to obtain search words;

And searching the search word in the standard dictionary, determining the search word as the text word of the text data when the standard word which is the same as the search word is searched from the standard dictionary, and returning to the text dividing step to perform text dividing according to a preset second length until the number of times of the text dividing reaches a preset number of times, so as to obtain the text word corresponding to the text data.

Optionally, the determining whether the user feature is in a target degradation feature includes:

Constructing an index for each feature in the target degradation features;

searching in the target degradation characteristic according to the user characteristic and the index to obtain search content;

detecting the length of the search content, and determining that the user characteristic is not in the target degradation characteristic when the length of the search content is zero;

and when the length of the search content is not zero, determining that the user characteristic is in the target degradation characteristic.

Optionally, the calling the resource recommendation list stored in association with the user to recommend the resource to the user includes:

extracting a user ID in the resource recommendation request;

generating a resource recommendation list calling request according to the user ID;

Invoking a resource recommendation list stored in association with the user by using the resource list invoking request;

And recommending the resources to the user by using the resource recommendation list.

In order to solve the above problems, the present invention further provides a resource recommendation device based on intelligent degradation, the device comprising:

the identification extraction module is used for acquiring a resource recommendation request of a user and extracting an access identification in the resource recommendation request;

The first recommending module is used for determining the resource recommending request as a first request if the access identifier is a first identifier, generating a resource recommending list according to a first strategy to recommend resources to the user, and storing the resource recommending list and the user in an associated mode;

The data acquisition module is used for determining that the resource recommendation request is a non-first request if the access identifier is a second identifier, and acquiring prestored user characteristics and target degradation characteristics;

The degradation judging module is used for judging whether the user characteristics are in target degradation characteristics or not;

The second recommendation module is used for generating a resource recommendation list according to the first strategy to recommend resources to the user if the user characteristics are not in the target degradation characteristics, and storing the resource recommendation list and the user in an associated mode;

And the third recommending module is used for calling a resource recommending list stored in association with the user to recommend the resource to the user if the user characteristic is in the target degradation characteristic.

In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:

A memory storing at least one instruction; and

And the processor executes the instructions stored in the memory to realize the intelligent degradation-based resource recommendation method.

In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having at least one instruction stored therein, the at least one instruction being executed by a processor in an electronic device to implement the above-mentioned intelligent degradation-based resource recommendation method.

The embodiment of the invention extracts the access identifier in the resource recommendation request, judges the access identifier to determine whether the resource recommendation request is a first request, and if so, generates a resource recommendation list of the user according to a first strategy to realize resource recommendation of the user, and stores the resource recommendation list to realize fine recommendation of the user of the first request; if the request is not the first request, the user characteristics are acquired, a resource recommendation list of the user is generated for the user corresponding to the user characteristics which are not in the target degradation characteristics, fine recommendation is performed, degradation recommendation is performed for the user corresponding to the user characteristics in the target degradation characteristics through the resource recommendation list generated through calling history, differential resource recommendation for different user groups is realized, indiscriminate recommendation service degradation for all users is avoided, further intelligent degradation of the resource recommendation service is realized when the server cannot normally provide recommendation service, and the utilization rate of computing resources in the server is improved. Therefore, the intelligent degradation-based resource recommendation method, the intelligent degradation-based resource recommendation device, the intelligent degradation-based resource recommendation electronic device and the intelligent degradation-based resource recommendation computer-readable storage medium can solve the problem that computing resources are empty when recommended services of users are degraded.

Drawings

FIG. 1 is a flowchart of a resource recommendation method based on intelligent degradation according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of generating a resource recommendation list and performing resource recommendation according to an embodiment of the present invention;

FIG. 3 is a flow chart of generating a user representation according to an embodiment of the present invention;

FIG. 4 is a functional block diagram of a resource recommendation device based on intelligent degradation according to an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of an electronic device implementing the resource recommendation method based on intelligent degradation according to an embodiment of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the application provides a resource recommendation method based on intelligent degradation. The execution subject of the resource recommendation method based on intelligent degradation comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the intelligent degradation-based resource recommendation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Referring to fig. 1, a flowchart of a resource recommendation method based on intelligent degradation according to an embodiment of the present invention is shown. In this embodiment, the resource recommendation method based on intelligent degradation includes:

S1, acquiring a resource recommendation request of a user, and extracting an access identifier in the resource recommendation request.

In the embodiment of the present invention, the resource recommendation request is a request for obtaining a recommended resource for a user, where the recommended resource includes but is not limited to: current politics, news information, entertainment information.

The resource recommendation request can be uploaded by a user through a page used for collecting the resource recommendation request in the client, or the resource recommendation request can be generated according to recommendation requirements input by the user through a pre-installed resource recommendation request generation program.

In one practical application scenario of the present invention, the resource recommendation request includes a plurality of pieces of information, such as a user ID, a request access identifier, etc., where the request access identifier may determine whether the resource recommendation request is a first request.

Because the resource recommendation request is often expressed in a fixed field sequence, for example, the resource recommendation request includes three fields, the first field is used for recording user information of the request, the second field is used for recording request identification, and the third field is used for recording a response mode of data; therefore, the resource recommendation request can be divided into a plurality of request fields by utilizing a field division mode, and the request identification used for recording in the resource recommendation request is selected for processing so as to extract the access identification in the resource recommendation request.

In the embodiment of the present invention, the extracting the access identifier in the resource recommendation request includes:

In detail, the field interval symbol is used for separating each field in the resource recommendation request, and the field interval symbol can be predefined by a user.

For example, there are resource recommendation requests: xxx < yyyy < zzz, wherein "<" is a field interval symbol, the resource recommendation request can be divided into three request fields according to the position of the field interval symbol, and the three request fields are numbered according to the sequence from front to back to obtain a request field number 1 xxx, a request field number 2 yyyyy and a request field number 3 zzz; and selecting a preset No. 2 request field, and analyzing the No. 2 request field to obtain a request identifier.

In other embodiments of the present invention, the access identifier may also be extracted from the resource recommendation request by a computer sentence (e.g., java sentence, python sentence, etc.) having a request identifier extraction function.

S2, judging the type of the access identifier, and executing the following S3 when the access identifier is a first identifier, or executing the following S4 when the access identifier is a second identifier.

S3, determining the resource recommendation request as a first request, generating a resource recommendation list according to a first strategy, recommending the resources of the user, and storing the resource recommendation list and the user in an associated mode.

In the embodiment of the invention, the first identifier is used for marking the resource recommendation request as a first request, if the access expression is the same as the first identifier, the resource recommendation request is determined to be the first request, and a resource recommendation list is required to be generated according to a first strategy so as to utilize the resource recommendation list to recommend resources to the user.

In detail, the first policy is an intelligent recommendation policy, that is, user data is analyzed by acquiring the user data, so as to implement targeted resource recommendation for the user according to an analysis result.

In the embodiment of the present invention, referring to fig. 2, the generating a resource recommendation list according to the first policy to recommend resources to the user includes:

s21, acquiring user data of the user, and generating a user portrait of the user according to the user data;

s22, acquiring a plurality of resources to be recommended, and respectively carrying out matching analysis on the plurality of resources to be recommended and the user portrait to obtain the matching degree of each resource to be recommended and the user portrait;

S23, selecting resources to be recommended, the matching degree of which is greater than a preset matching degree threshold value, and sorting the selected resources to be recommended according to the sequence of the matching degree from large to small to generate a resource recommendation list;

s24, recommending the resources to the user according to the resource recommendation list.

In detail, the user data includes, but is not limited to, age, gender, occupation, and interests of the user, and the user data may be acquired in various forms (e.g., video, image, text, etc.) in order to generate a more accurate representation of the user.

Embodiments of the present invention may analyze the user data to generate a user representation of the user data through pre-trained smart models including, but not limited to, OCR (Optical Character Recognition ) models, NLP (Natural Language Processing, natural language processing) models, ASR (Automatic Speech Recognition ) models, and the like.

In one embodiment of the present invention, referring to fig. 3, the generating a user portrait of the user according to the user data includes:

s31, performing text conversion on the user data to obtain text data;

s32, performing word segmentation processing on the text data to obtain text word segmentation;

s33, carrying out word vector conversion on the text word segmentation to obtain text word vectors;

s34, carrying out feature extraction on the text word vector by utilizing a pre-trained feature extraction algorithm to obtain a feature word vector;

s35, generating a user portrait of the user according to the feature word vector.

For example, the user data includes image data and video data, and the OCR model may be used to process the image data in the user data to convert the image data into text data; and processing the video data in the user data by utilizing the combination of the ASR model and the OCR model to convert the video data into text data.

The embodiment can use a pre-built standard dictionary to segment the text data, wherein the standard dictionary comprises a plurality of standard segments. For example, the text data is divided according to different lengths, the division result is searched in the standard dictionary, and if the standard word identical to the division result can be searched, the standard word is determined to be the text word of the text data.

In one embodiment of the present invention, the word segmentation processing is performed on the text data to obtain text word segmentation, including:

For example, the text data is divided according to different preset lengths, and the search words obtained by dividing the text in each time are searched in the dictionary to obtain text word segmentation until the number of times of dividing the text reaches the preset number of times, so that word segmentation of the text data is realized.

In this embodiment, the text data is divided and retrieved according to different lengths, so that the text data is divided, the content of the text data is not required to be analyzed, and the efficiency of word division of the text data is improved.

In this embodiment, a preset word2vec model may be used to convert the text word segmentation into a text word vector.

Further, the feature extraction algorithm includes, but is not limited to, a bayesian classification algorithm, a logistic regression algorithm, a KNN algorithm, and the like, and features of the text word vectors are extracted by using the feature extraction algorithm to obtain feature word vectors, and the feature word vectors are collected to obtain a user portrait of the user.

In the embodiment of the present invention, the plurality of resources to be recommended are selectable resources that are recommended to the user, for example, politics, news information, entertainment information, and the like.

According to the embodiment of the invention, the matching analysis of the plurality of resources to be recommended and the user portrait can be respectively carried out by utilizing a preset matching algorithm, so that the matching degree of each resource to be recommended and the user portrait can be obtained, and the matching algorithm comprises a Euclidean distance algorithm, a cosine distance algorithm and the like.

According to the embodiment of the invention, the matching value between each resource to be recommended and the user portrait is calculated through a preset matching algorithm, and a resource recommendation list is generated according to the sequence of the matching values from large to small, so that the resource recommendation of the user is realized according to the resource recommendation list.

For example, there are a resource 1 to be recommended, a resource 2 to be recommended, a resource 3 to be recommended and a resource 4 to be recommended, and after calculation, it is known that the matching value of the resource 1 to be recommended and the user portrait is 80, the matching value of the resource 2 to be recommended and the user portrait is 94, the matching value of the resource 3 to be recommended and the user portrait is 75, and the matching value of the resource 4 to be recommended and the user portrait is 83, and then a resource recommendation list is generated according to the order of the matching values from high to low: the method comprises the steps of recommending resources 2, recommending resources 4, recommending resources 1 and recommending resources 3; and recommending the resources to the user according to the sequence of the resources to be recommended in the resource recommendation list.

Further, after the resource recommendation list is generated, the embodiment of the invention stores the resource recommendation list in association with the user.

For example, by generating a connection associated with a user ID in the resource recommendation list, when the user ID is clicked, the resource recommendation list associated with the user ID may be invoked to enable the resource recommendation list to be stored in association with the user.

Or the resource recommendation list can be stored in a pre-constructed database, and named by a user ID, so that the resource recommendation list and the user can be stored in a correlated way.

S4, determining the resource recommendation request as a non-first request, and acquiring prestored user characteristics and target degradation characteristics.

In the embodiment of the present invention, the second identifier is used to mark the resource recommendation request as a non-first request, and if the access expression is the same as the second identifier, it is determined that the resource recommendation request is a non-first request, and a user feature and a target degradation feature that are stored in advance need to be obtained.

In detail, the user characteristics are data related to the user, such as user address, user age, user gender, etc., which can classify the user.

The target degradation characteristic is a user characteristic which needs to be subjected to degradation recommendation and can be preset. For example, the target degradation characteristics set in advance are: addresses are users in wide and deep North; and recommending and degrading the users with the user addresses of wide and deep North and North in the user characteristics.

Specifically, the downgrade recommendation refers to downgrade an accurate resource recommendation to a non-accurate resource recommendation. For example, the original accurate resource recommendation is performed on each user according to the user characteristics, and the resource recommendation is performed on all users according to a preset template.

According to the embodiment of the invention, the user characteristic and the target degradation characteristic can be captured from the preset blockchain node through the python statement with the data capturing function, and the efficiency of acquiring the user characteristic and the target degradation characteristic from the blockchain can be improved by utilizing the high throughput of the blockchain on the data.

S5, judging whether the user characteristic is in the target degradation characteristic, and executing S6 below when the user characteristic is not in the target degradation characteristic, or executing S7 below when the user characteristic is in the target degradation characteristic.

In the embodiment of the invention, whether the user characteristic is in the target degradation characteristic can be judged by a retrieval mode.

In detail, the determining whether the user feature is in a target degradation feature includes:

Constructing an index for each feature in the target degradation features;

In detail, the retrieval may be a pointer constructed from any one of the target features, by which the feature may be uniquely retrieved. Thus, by constructing the index, data retrieval can be performed uniquely and quickly.

Further, the invention can detect the length of the search content by using a java sentence with a field detection function. For example, a preset java sentence with a field detection function is executed on the search content to acquire a return value corresponding to the sentence, when the length of the search content is not zero, the length data of the search content is returned, and when the length of the search content is zero, null is returned.

Judging whether the user features are in the target degradation features according to the length of the retrieved content, and not needing to carry out detailed analysis on the retrieved content, thereby being beneficial to improving the efficiency of judging whether the user features are in the target degradation features.

S6, generating a resource recommendation list according to the first strategy, recommending resources for the user, and storing the resource recommendation list and the user in an associated mode.

In the embodiment of the present invention, if the user feature is not in the target degradation feature, a resource recommendation list may be generated according to the same first policy as in step S3, and the generated resource recommendation list is used to recommend resources to the user, and meanwhile, the resource recommendation list and the user are stored in association in the manner as in step S3, which is not described herein.

S7, calling a resource recommendation list stored in association with the user to recommend the resource to the user.

In the embodiment of the invention, if the user characteristic is in the target degradation characteristic, the user is determined to be subjected to resource recommendation, so that a resource recommendation list stored in association with the user can be called, and the user is subjected to resource recommendation through the called resource recommendation list.

In one embodiment of the present invention, the calling the resource recommendation list stored in association with the user to recommend resources to the user includes:

extracting a user ID in the resource recommendation request;

In detail, the step of extracting the user ID in the resource recommendation request is consistent with the step of extracting the access identifier in the resource recommendation request in step S1, which is not described herein.

Specifically, a preset compiler can be utilized to compile a resource recommendation list calling request according to the user ID, and the resource recommendation list calling request can realize the calling of a resource recommendation list which is stored in an associated mode by the user ID.

Further, the step of recommending the resources to the user by using the resource recommendation list is consistent with the step of recommending the resources to the user in step S3, which is not described herein.

The embodiment of the invention extracts the access identifier in the resource recommendation request, judges the access identifier to determine whether the resource recommendation request is a first request, and if so, generates a resource recommendation list of the user according to a first strategy to realize resource recommendation of the user, and stores the resource recommendation list to realize fine recommendation of the user of the first request; if the request is not the first request, the user characteristics are acquired, a resource recommendation list of the user is generated for the user corresponding to the user characteristics which are not in the target degradation characteristics, fine recommendation is performed, degradation recommendation is performed for the user corresponding to the user characteristics in the target degradation characteristics through the resource recommendation list generated through calling history, differential resource recommendation for different user groups is realized, indiscriminate recommendation service degradation for all users is avoided, further intelligent degradation of the resource recommendation service is realized when the server cannot normally provide recommendation service, and the utilization rate of computing resources in the server is improved. Therefore, the resource recommendation method based on intelligent degradation can solve the problem that computing resources are empty when the recommended service of the user is degraded.

FIG. 4 is a functional block diagram of a resource recommendation device based on intelligent degradation according to an embodiment of the present invention.

The resource recommendation device 100 based on intelligent degradation can be installed in an electronic device. Depending on the implemented functionality, the intelligent downgraded resource recommendation apparatus 100 may include an identification extraction module 101, a first recommendation module 102, a data acquisition module 103, a degradation determination module 104, a second recommendation module 105, and a third recommendation module 106. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

In the present embodiment, the functions concerning the respective modules/units are as follows:

the identifier extraction module 101 is configured to obtain a resource recommendation request of a user, and extract an access identifier in the resource recommendation request;

the first recommending module 102 is configured to determine that the resource recommending request is a first request when the access identifier is determined to be a first identifier, generate a resource recommending list according to a first policy, and store the resource recommending list in association with the user;

The data obtaining module 103 is configured to determine that the resource recommendation request is a non-first request when the access identifier is determined to be the second identifier, and obtain a user feature and a target degradation feature that are stored in advance;

the degradation determination module 104 is configured to determine whether the user feature is in a target degradation feature;

The second recommendation module 105 is configured to generate a resource recommendation list according to the first policy to recommend resources to the user when the user feature is not in the target degradation feature, and store the resource recommendation list in association with the user;

and the third recommending module 106 is configured to invoke a resource recommending list stored in association with the user to recommend resources to the user when the user feature is in the target degradation feature.

In detail, each module in the resource recommendation device 100 based on intelligent degradation in the embodiment of the present invention adopts the same technical means as the resource recommendation method based on intelligent degradation described in fig. 1 to 3, and can generate the same technical effects, which is not described herein.

Fig. 5 is a schematic structural diagram of an electronic device implementing a resource recommendation method based on intelligent degradation according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a resource recommendation program based on intelligent degradation.

The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of resource recommendation programs based on intelligent degradation, but also for temporarily storing data that has been output or is to be output.

The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes programs or modules (e.g., a resource recommendation program based on intelligent degradation, etc.) stored in the memory 11 by running or executing the programs or modules, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.

The bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

Fig. 5 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.

For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.

Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.

The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

The intelligent downgraded resource recommendation program stored in the memory 11 of the electronic device 1 is a combination of instructions which, when executed in the processor 10, may implement:

In particular, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 3, which are not repeated herein.

Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A resource recommendation method based on intelligent degradation, the method comprising:

if the user characteristics are in the target degradation characteristics, invoking a resource recommendation list stored in association with the user to recommend resources to the user;

Wherein the determining whether the user feature is in a target degradation feature comprises: constructing an index for each feature in the target degradation features; searching in the target degradation characteristic according to the user characteristic and the index to obtain search content; detecting the length of the search content, and determining that the user characteristic is not in the target degradation characteristic when the length of the search content is zero; when the length of the search content is not zero, determining that the user feature is within the target degradation feature;

The calling the resource recommendation list stored in association with the user to recommend the resource to the user comprises the following steps: extracting a user ID in the resource recommendation request; generating a resource recommendation list calling request according to the user ID; invoking a resource recommendation list stored in association with the user by using the resource recommendation list invoking request; and recommending the resources to the user by using the resource recommendation list.

2. The intelligent downgrade-based resource recommendation method of claim 1, wherein the extracting the access identifier in the resource recommendation request comprises:

3. The intelligent downgrade-based resource recommendation method of claim 1, wherein generating a resource recommendation list according to a first policy for recommending resources to the user comprises:

4. The intelligent downgrade-based resource recommendation method of claim 3, wherein the generating a user representation of the user from the user data comprises:

performing text conversion on the user data to obtain text data;

5. The intelligent degradation-based resource recommendation method according to claim 4, wherein the word segmentation processing is performed on the text data to obtain text words, and the method comprises:

6. An intelligent downgrade based resource recommendation apparatus for implementing the intelligent downgrade based resource recommendation method according to any one of claims 1 to 5, the apparatus comprising:

the first recommending module is used for determining the resource recommending request as a first request when the access identifier is a first identifier, generating a resource recommending list according to a first strategy, recommending the resource for the user, and storing the resource recommending list and the user in an associated mode;

The data acquisition module is used for determining that the resource recommendation request is a non-first request when the access identifier is a second identifier, and acquiring prestored user characteristics and target degradation characteristics;

The second recommendation module is used for generating a resource recommendation list according to the first strategy to recommend resources to the user when the user characteristics are not in the target degradation characteristics, and storing the resource recommendation list and the user in a correlated way;

And the third recommendation module is used for calling a resource recommendation list stored in association with the user to recommend resources to the user when the user characteristics are in the target degradation characteristics.

7. An electronic device, the electronic device comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the intelligent downgrade based resource recommendation method of any one of claims 1 to 5.

8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the intelligent downgrade based resource recommendation method according to any one of claims 1 to 5.