CN118013127A - Resource data recommendation processing method and device - Google Patents

Abstract

The embodiment of the specification provides a resource data recommendation processing method and device, wherein the resource data recommendation processing method comprises the following steps: in the data recommendation process of the resource item, starting from item related data of the resource item, converting the item related data into converted item data, constructing recommendation input data according to the converted item data and recommendation data configuration of the resource item, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, obtaining recommendation metadata, further, constructing recommendation data of the resource item based on the recommendation metadata, and performing recommendation processing of the recommendation data to a recommendation channel of the resource item, so that recommendation data generation and recommendation processing of the resource item are realized.

Description

Resource data recommendation processing method and device

Technical Field

The present document relates to the field of data processing technologies, and in particular, to a method and an apparatus for recommending and processing resource data.

Background

With the continuous development and popularization of the internet, the application range of online services provided based on the internet is wider and wider, so that most users are gradually covered, various online service scenes, such as scenes of marketing material distribution of project products in an online manner, are presented, the distribution of the marketing material is required to display the performance or potential of the project products, and the revenue or income situation of the project products is presented in an easy-to-understand manner, which is a great challenge for the providers of many project products.

Disclosure of Invention

One or more embodiments of the present disclosure provide a resource data recommendation processing method, including: and carrying out data conversion processing on the project related data of the resource project to obtain converted project data. And constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata. And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

One or more embodiments of the present disclosure provide a resource data recommendation processing apparatus, including: the data conversion module is configured to perform data conversion processing on project related data of the resource project to obtain converted project data. The data generation module is configured to construct recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, input the recommendation input data into a recommendation data generation model to generate recommendation data, and obtain recommendation metadata. And the recommendation processing module is configured to construct recommendation data of the resource items based on the recommendation metadata and conduct recommendation processing of the recommendation data to recommendation channels of the resource items.

One or more embodiments of the present specification provide a resource data recommendation processing apparatus including: a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: and carrying out data conversion processing on the project related data of the resource project to obtain converted project data. And constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata. And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

One or more embodiments of the present specification provide a computer-readable storage medium storing computer-executable instructions that, when executed, implement the following: and carrying out data conversion processing on the project related data of the resource project to obtain converted project data. And constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata. And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

Drawings

For a clearer description of one or more embodiments of the present description or of the solutions of the prior art, the drawings that are needed in the description of the embodiments or of the prior art will be briefly described below, it being obvious that the drawings in the description that follow are only some of the embodiments described in the present description, from which other drawings can be obtained, without inventive faculty, for a person skilled in the art;

FIG. 1 is a schematic diagram of an implementation environment of a resource data recommendation processing method according to one or more embodiments of the present disclosure;

FIG. 2 is a process flow diagram of a method for recommending and processing resource data according to one or more embodiments of the present disclosure;

FIG. 3 is a process flow diagram of a model training process provided in one or more embodiments of the present disclosure;

FIG. 4 is a process flow diagram of a method for processing resource data recommendations for a marketing recommendation scenario, in accordance with one or more embodiments of the present disclosure;

FIG. 5 is a process flow diagram of a resource data recommendation processing method for a rights and interests item recommendation scenario according to one or more embodiments of the present disclosure;

FIG. 6 is a schematic diagram of an embodiment of a resource data recommendation processing device according to one or more embodiments of the present disclosure;

fig. 7 is a schematic structural diagram of a resource data recommendation processing device according to one or more embodiments of the present disclosure.

Detailed Description

In order to enable a person skilled in the art to better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one or more embodiments of the present disclosure without inventive effort, are intended to be within the scope of the present disclosure.

The resource data recommendation processing method provided in one or more embodiments of the present disclosure may be applied to an implementation environment of resource item recommendation, and referring to fig. 1, the implementation environment includes at least:

A server 101 for acquiring, processing and recommending data of resource items, a recommended data generation model 102 for generating recommended data according to the input of the resource items input by the server 101, and a delivery terminal 103 for receiving the data recommendation of the server 101;

The server 101 may be a server, or a server cluster formed by a plurality of servers, or one or more cloud servers in a cloud computing platform; the recommended data generating model 102 may be a generating model for generating recommended metadata according to data input recommendation, which is obtained after fine tuning of the pre-training model; the delivery terminal 103 may be a cell phone, a computer, a tablet computer, an e-book reader, a VR (Virtual Reality technology) -based information interaction device, an in-vehicle terminal, an IoT device, a wearable smart device, a laptop, a desktop computer, an advertising terminal, etc.

In this implementation environment, in the process of data recommendation for a resource item, the server 101 performs data conversion processing on item related data of the resource item to be recommended, constructs recommendation input data for inputting the recommendation data generation model 102 according to conversion item data obtained by the conversion processing and recommendation data configuration of the resource item configured in advance, inputs the recommendation input data into the recommendation data generation model 102 to generate corresponding recommendation metadata, further constructs recommendation data of the resource item based on the recommendation metadata, and performs recommendation processing of the recommendation data to recommendation channels configured in advance for the resource item, thereby recommending the recommendation data of the resource item to corresponding delivery devices 103 of the recommendation channels configured in advance.

One or more embodiments of a resource data recommendation processing method provided in the present specification are as follows:

referring to fig. 2, the method for processing resource data recommendation provided in this embodiment specifically includes steps S202 to S206.

Step S202, carrying out data conversion processing on project related data of resource projects to obtain converted project data.

The resource item in this embodiment may be an item for performing resource management, where the managed resource may be a fund resource, a equity asset, or a virtual resource, and correspondingly, the resource item may be a fund management item, an equity asset management item, or a virtual resource management item; wherein the fund management items include financial items, and the equity asset management items include equity asset management items under asset varieties (funds, stocks, bonds) available for trade; virtual resource management items include coupons, points, and the like.

The item-related data of the resource item includes data related to the resource item, data related to an item domain or an item category of the resource item, data related to a recommendation of the resource item, and/or data related to an item equity of the resource item.

For example, the data related to the resource item may include data related to a manager or manager of the current resource item, and may further include data related to a release time, a management period, an item index, etc. of the current resource; the data related to the project field of the resource project can be news articles, analysis reports, market comments, financial blogs and the like related to equity assets; data related to recommendations for resource items, behavior related data for a target user group of equity assets; data related to the rights and interests of the resource items, historical rights and interests of the resource items, and the like.

In the concrete implementation, in the process of recommending the data of the resource item, in order to enable the data recommendation aiming at the resource item to reflect the current situation of the resource item in time, the item related data of the resource item can be acquired in real time, so that the timeliness of the data recommendation of the resource item is ensured; further, in order to improve diversity and comprehensiveness of data recommendation, in the process of acquiring the item-related data of the resource item, the item-related data of the resource item is acquired from a plurality of data sources, and in particular, in an alternative implementation manner, before performing data conversion processing on the item-related data of the resource item, the following manner is adopted to acquire the item-related data of the resource item:

Determining a plurality of data sources of the resource project according to the recommended scene category of the resource project, and acquiring project data of the resource project from the plurality of data sources;

And carrying out de-duplication processing on the acquired project data to acquire the project related data.

Wherein the plurality of data sources of the resource item comprises: a data source of data related to a resource item, a data source of data related to a project domain or project classification of a resource item, a data source of data related to a recommendation of a resource item, and/or a data source of data related to a project equity of a resource item.

In a specific implementation, in a process of converting project related data of a resource project into converted project data, in an optional implementation provided in this embodiment, performing data conversion processing on the project related data of the resource project to obtain converted project data includes: filtering the project related data to obtain filtered project data; performing data annotation on the filtered item data to obtain annotated item data; and carrying out data conversion on the marked item data to obtain converted item data.

In addition, in the process of converting the project related data of the resource project into the converted project data, the converted project data can be obtained by carrying out data labeling on the project related data and carrying out data conversion on the obtained labeled project data.

Specifically, in the process of filtering the project-related data, the embodiment filters the project-related data from two filtering dimensions, namely noise data filtering and invalid data filtering, so as to improve the accuracy of filtering the project-related data, and in an optional implementation manner provided in this embodiment, the filtering process is performed on the project-related data to obtain filtered project data, which includes:

identifying noise data contained in the project related data, and deleting the noise data from the project related data;

Analyzing the deleted project related data, deleting the access invalid data obtained by analysis, and obtaining the filtered project data. The invalid access data may be a link or the like that triggers an invalidation or a failure to trigger.

In this embodiment, in the process of converting the project related data of the resource project into the converted project data, the filtered project data is subjected to data labeling, so that the follow-up recommended data generation model is helped to understand the converted project data more accurately and effectively on the basis of the type label obtained by the data labeling, and in an optional implementation manner provided in this embodiment, the filtered project data is subjected to data labeling to obtain labeled project data, which includes:

Performing word segmentation processing on the filtered project data to obtain project keywords;

and marking type labels based on the word types of the item keywords, and obtaining the marked item data marked with the type labels.

And step S204, constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata.

In this embodiment, in the process of recommending the data of the resource item, the data of the resource item can be correspondingly configured, and different requirements of different resource items on the data recommendation are embodied through configuration, so that personalized data recommendation is realized at the granularity of the resource item in the process of recommending the data of the resource item, and the recommended data configuration refers to the pre-configured data requirement of recommending the data of the resource item.

In the specific execution process, the recommended data configuration can be configured and generated through a recommended data configuration page, so that the recommended data configuration page can be intuitively and conveniently configured, further, the recommended data template can be configured on the recommended data configuration page for improving the flexibility and convenience of configuration, and the recommended data template can be configured in an editing mode on the basis that the recommended data template is edited, namely: and the recommended data configuration is generated by configuring a recommended data template displayed on a recommended data configuration page. Specifically, the recommended data configuration includes at least one of the following: data attention level configuration, language type configuration and data visualization configuration.

The data focus level configuration refers to configuration information of the generated content focused on after marking the content focused on in the data recommendation process of the resource item, for example, if focusing on the fund index of the fund management item is required, the fund index focused on can be marked.

The language type configuration is configuration information generated after the pointer configures the language or style of the data recommendation of the resource item; for example, in the data recommendation process of the fund management item, in order to invite the user to join in the fund management item, the language of the recommended data can be configured into the offer language of which the language is more passenger; and for example, configuring specific content in the recommended data as a content style configuration of the content style.

The data visualization configuration refers to configuration information generated after the configuration of the data visualization form of the data recommendation of the resource item, for example, in the data recommendation process of the fund management item, the designated data is configured into a chart configuration displayed in a chart form.

In practical applications, in the process of generating the recommended data based on two data, namely, the converted project data and the recommended data configuration of the resource project required by the data generation, the recommended data generation model generates the recommended data based on the converted project data and the recommended data configuration of the resource project, where the recommended data generation model generates the recommended data may limit the format of the input data, for example, the requirement on the input data is an input prompt file.

In view of this, according to the conversion project data and the recommended data configuration of the resource project, the recommended input data is constructed to be used as the input of the recommended data generation model, and in particular, in an optional implementation manner provided in this embodiment, the construction of the recommended input data according to the conversion project data and the recommended data configuration of the resource project includes:

Analyzing the conversion project data and the recommended data configuration;

And filling the analysis result into an input data template of the recommended data generation model, and taking the input data file obtained after filling as the recommended input data.

For example, the conversion project data and the recommended data configuration are parsed, the parsed content of the conversion project data and the parsed content of the recommended data configuration are obtained, a template of a prompt (prompt word) of the model is generated according to the recommended data, the parsed content of the recommended data configuration is added to the question portion of the template, the parsed content of the converted project data after parsing is added to the data portion of the template, a prompt file for inputting the recommendation data generation model is obtained.

It should be noted that, in practical application, there may be a case where the recommendation data generation model does not set a data input limit or rule, or a case where the conversion item data accords with the data input limit or rule of the recommendation data generation model, for this purpose, the conversion item data and the recommendation data configuration of the resource item may be directly input into the recommendation data generation model to generate recommendation data, so as to obtain recommendation metadata, that is: the process of constructing the recommendation input data according to the configuration of the recommendation data of the conversion project data and the resource project, and inputting the recommendation input data into the recommendation data generation model to generate the recommendation data may be replaced by a process of inputting the configuration of the recommendation data of the conversion project data and the resource project into the recommendation data generation model to generate the recommendation data.

In the specific implementation, recommendation input data is input into a recommendation data generation model to generate recommendation data on the basis of obtaining recommendation input data according to recommendation data configuration construction of conversion project data and resource projects, and recommendation metadata is obtained. The recommended metadata refers to data recommended contents generated by the recommended data generation model according to the conversion item data and the recommended data configuration, and the data recommended contents need to be recommended by a further data constructor, so the recommended metadata is called as recommended metadata.

The recommended data generation model is a data generation model obtained after further training or fine tuning according to the pre-training model, the model inputs recommended data configuration comprising conversion project data and resource projects, and the trained or fine-tuned data generation model can generate recommended data according to the conversion project data and the recommended data configuration of the resource projects, obtain recommended metadata and output the recommended metadata. Pre-training models, which refer to pre-trained natural language models, may employ neural network architectures that include large quantities of parameters, pre-training models may employ pre-trained large language models (Large Language Model, LLM), such as conversational interaction models in the conversational interaction domain, or generative models in the content generation domain.

As described above, the recommended data configuration includes at least one of the data attention level configuration, the language type configuration, and the data visualization configuration, and the process of generating the recommended data by the recommended data generation model will be specifically described herein taking the recommended data configuration including the data attention level configuration and the data visualization configuration as an example.

By way of example, the recommendation data generation by the recommendation data generation model includes: generating recommended data text according to the conversion project data according to the data attention level configuration; and extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visual configuration.

In addition, in the case where the recommended data configuration includes a language type configuration and a data visualization configuration, the recommended data generation by the recommended data generation model includes: according to the language type configuration, generating a recommended data text according to the converted project data; extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visual configuration; or in the case that the recommended data configuration includes a data focus level configuration, a language type configuration and a data visualization configuration, the recommended data generation by the recommended data generation model includes: generating a recommended data text according to the converted project data according to the data attention level configuration and the language type configuration; and extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visual configuration.

In this embodiment, the recommendation data generation model is obtained by further training or fine tuning the pre-training model, and the input of the recommendation data generation model includes the conversion project data and the recommendation data configuration of the resource project, and the recommendation data generation model after training or fine tuning can generate the recommendation data according to the conversion project data and the recommendation data configuration of the resource project, obtain and output the recommendation metadata, where in an optional implementation manner provided in this embodiment, the recommendation data generation model is obtained by adopting the following manner:

fine tuning the pre-training model based on a pre-marked project data set to obtain an intermediate model;

And testing the intermediate model based on a test data set, and carrying out parameter adjustment on the intermediate model according to a test result to obtain the recommended data generation model.

The pre-training model can be obtained by performing model training on the model to be trained based on corpus samples in a corpus.

For example, the training process of the recommended data generation model specifically includes the following steps:

step S302, data acquisition

Data acquisition from a plurality of data sources of a resource item specifically comprises: acquiring relevant data of a manager or manager of a current resource project, acquiring data related to the release time, management period, project index and the like of the current resource project, news articles, analysis reports, market comments, financial blogs and the like related to the resource project, behavior relevant data of a target user group of the resource project, and data related to historical rights and interests index and the like of the resource project;

step S304, data preprocessing

Firstly, identifying noise data contained in acquired data, and deleting the noise data from the acquired data;

Then analyzing the deleted data, and deleting access invalid data such as trigger invalidation or link failure obtained by analysis;

secondly, marking the deleted data, and performing data conversion on the marked data to obtain sample data; step S306, model pre-training

Selecting a model architecture (such as Transformers architecture), constructing a model to be trained on the basis of the selected model architecture, training the model to be trained by using sample data, and obtaining a pre-training model after training is completed; wherein training tasks, such as training tasks for learning context and inter-vocabulary relationships, can be set in the training process;

Step S308, fine tuning of the Pre-trained model

Utilizing a specific data set in the field of recommending the pre-labeled resource item data to finely tune the pre-training model so as to adjust model parameters of the pre-training model and obtain a recommended data generation model; specific data generation tasks such as a marketing document generation task and a resource management suggestion generation task can be set in the fine tuning process;

Step S310, model test

Testing the fine-tuned pre-training model by using a test data set independent of the specific data set, and optimizing model parameters of the fine-tuned pre-training model according to a test result to obtain a recommended data generation model;

step S312, model optimization update

In the actual application process of the recommendation data generation model, further parameter optimization and adjustment can be performed on the recommendation data generation model according to the feedback result or the evaluation result of the recommendation metadata generated by the recommendation data generation model.

And step S206, recommendation data of the resource items are established based on the recommendation metadata, and recommendation processing of the recommendation data is carried out on recommendation channels of the resource items.

In a specific implementation scene, after the recommendation metadata of the resource item is obtained through the recommendation data generation model, the recommendation data of the resource item is built based on the recommendation metadata, so that the recommendation data for recommending the recommendation channel of the resource item is obtained, and the recommendation processing of the recommendation data is carried out on the recommendation channel of the resource item.

In an optional implementation manner provided in this embodiment, the constructing recommendation data of the resource item based on the recommendation metadata includes: performing data assembly on the recommendation metadata according to the delivery equipment parameters of the recommendation channel to obtain the recommendation data; or according to a data assembly strategy corresponding to the type of the delivery equipment of the recommendation channel, carrying out data assembly on the recommendation metadata to obtain the recommendation data.

In practical application, the recommendation channel of the resource item can be pre-configured, and the delivery equipment list of the resource item in the configured recommendation channel can be further configured, so that automatic data recommendation processing can be performed on the basis of the pre-configured delivery equipment list of the recommendation channel. Specifically, in an optional implementation manner provided in this embodiment, the recommending processing of the recommendation data to the recommendation channel of the resource item includes: recommending the recommendation data to the delivery equipment in the delivery equipment list of the recommendation channel by the delivery equipment, so that the recommendation data is displayed on the delivery equipment.

In summary, in the resource data recommendation processing method provided by the embodiment, in the process of recommending the data of the resource item, the item related data of the resource item is obtained in real time, so that the obtained item related data can reflect the current situation of the resource item in time, thereby ensuring timeliness of data recommendation of the resource item; on the basis, data conversion processing is carried out on item related data of resource items to obtain converted item data, recommendation input data is built according to the converted item data and preset recommendation data configuration of the resource items and is used as input of a recommendation data generation model, data recommendation individualization is embodied through the recommendation data configuration, flexibility and convenience of data recommendation are improved, recommendation metadata are obtained through recommendation data generation carried out by inputting the recommendation input data into the recommendation data generation model, recommendation data of the resource items are built based on the recommendation metadata, the built recommendation data can be matched with data recommendation requirements of recommendation channels of the preset resource items, finally recommendation processing of the recommended data is carried out on the recommendation channels of the resource items, and high-efficiency and rapid automatic data recommendation of the resource items is achieved.

The following further describes the resource data recommendation processing method provided in this embodiment with reference to fig. 4 by taking an application of the resource data recommendation processing method provided in this embodiment to a marketing recommendation scene as an example, and referring to fig. 4, the resource data recommendation processing method applied to the marketing recommendation scene specifically includes the following steps.

Step S402, determining a plurality of data sources of the resource item according to the recommended scene category of the resource item, and acquiring item data of the resource item from the plurality of data sources.

Step S404, filtering the acquired project data to obtain filtered project data.

Step S406, data labeling is carried out on the filtered item data, and labeled item data is obtained.

Step S408, data conversion is carried out on the marked item data to obtain converted item data.

In step S410, the conversion project data and the recommended data configuration of the resource project are parsed, and the parsing result is filled into the input data template to obtain the input data file.

In step S412, the input data file is input into the recommendation data generation model to generate marketing recommendation data, and marketing recommendation metadata is obtained.

Step S414, according to the parameters of the throwing equipment of the recommendation channel of the resource item, carrying out data assembly on the marketing recommendation metadata to obtain marketing recommendation data.

Step S416, recommendation processing of marketing recommendation data is performed to the recommendation channels of the resource items.

It should be noted that any one step or any combination of steps from step S402 to step S416 may be replaced by the corresponding technical means provided in step S202 to step S206 according to the requirement of implementing deployment, which is not described herein.

The following takes an application of the resource data recommendation processing method provided in this embodiment in a rights item recommendation scenario as an example, and further describes the resource data recommendation processing method provided in this embodiment with reference to fig. 5, and referring to fig. 5, the resource data recommendation processing method applied in the rights item recommendation scenario specifically includes the following steps.

Step S502, word segmentation processing is carried out on the project related data of the equity project, and project keywords are obtained.

And step S504, carrying out type label marking based on the word type of the item keyword to obtain marked item data marked with type labels.

Step S506, data conversion is carried out on the marked item data, and converted item data is obtained.

Step S508, the recommended input data is constructed according to the converted project data and the language type configuration and the data visualization configuration of the rights and interests project.

And S510, inputting the recommended input data into a recommended data generation model to generate recommended data, and obtaining a recommended data text and a visual data component.

Optionally, the generating of the recommendation data by the recommendation data generating model includes: generating a recommended data text according to the converted project data according to the language type configuration; visual data in the conversion project data is extracted, and a visual data component is generated based on the visual data and the data visual configuration.

And S512, constructing recommendation data based on the recommendation data text and the visualized data component, and performing recommendation processing of the recommendation data on the recommendation channels of the equity items.

It should be noted that any one step or any combination of steps from step S502 to step S512 may be replaced by the corresponding technical means provided in step S202 to step S206 according to the requirement of implementing deployment, and will not be described in detail herein.

The embodiment of the resource data recommendation processing device provided in the present specification is as follows:

In the foregoing embodiments, a resource data recommendation processing method and a resource data recommendation processing device corresponding to the method are provided, and the description is given below with reference to the accompanying drawings.

Referring to fig. 6, a schematic diagram of an embodiment of a resource data recommendation processing device provided in this embodiment is shown.

Since the apparatus embodiments correspond to the method embodiments, the description is relatively simple, and the relevant portions should be referred to the corresponding descriptions of the method embodiments provided above. The device embodiments described below are merely illustrative.

The embodiment provides a resource data recommendation processing device, which comprises:

The data conversion module 602 is configured to perform data conversion processing on project related data of the resource project to obtain converted project data;

a data generating module 604, configured to construct recommendation input data according to the conversion project data and the recommendation data configuration of the resource project, and input the recommendation input data into a recommendation data generating model to generate recommendation data, so as to obtain recommendation metadata;

A recommendation processing module 606 configured to construct recommendation data of the resource item based on the recommendation metadata, and perform recommendation processing of the recommendation data to a recommendation channel of the resource item.

The embodiment of the resource data recommendation processing device provided in the present specification is as follows:

In response to the above description of a method for recommending and processing resource data, one or more embodiments of the present disclosure further provide a device for recommending and processing resource data, where the device for recommending and processing resource data is used to execute the above provided method for recommending and processing resource data, and fig. 7 is a schematic structural diagram of the device for recommending and processing resource data provided in one or more embodiments of the present disclosure.

The resource data recommendation processing device provided in this embodiment includes:

As shown in fig. 7, the resource data recommendation processing device may have a relatively large difference due to different configurations or performances, and may include one or more processors 701 and a memory 702, where the memory 702 may store one or more storage applications or data. Wherein the memory 702 may be transient storage or persistent storage. The application programs stored in the memory 702 may include one or more modules (not shown in the figures), each of which may include a series of computer-executable instructions in the resource data recommendation processing device. Still further, the processor 701 may be configured to communicate with the memory 702 and execute a series of computer executable instructions in the memory 702 on the resource data recommendation processing device. The resource data recommendation processing device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input/output interfaces 705, one or more keyboards 706, and the like.

In a particular embodiment, the resource data recommendation processing device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the resource data recommendation processing device, and the execution of the one or more programs by the one or more processors comprises computer executable instructions for:

carrying out data conversion processing on project related data of resource projects to obtain converted project data;

constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata;

And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

An embodiment of a computer-readable storage medium provided in the present specification is as follows:

In response to the above description of a resource data recommendation processing method, one or more embodiments of the present disclosure further provide a computer-readable storage medium based on the same technical concept.

The computer readable storage medium provided in this embodiment is configured to store computer executable instructions, where the computer executable instructions when executed implement the following procedures:

carrying out data conversion processing on project related data of resource projects to obtain converted project data;

constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata;

And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

It should be noted that, in the present specification, an embodiment of a computer readable storage medium and an embodiment of a resource data recommendation processing method in the present specification are based on the same inventive concept, so that a specific implementation of the embodiment may refer to an implementation of the foregoing corresponding method, and a repetition is omitted.

In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment focuses on differences from other embodiments, for example, an apparatus embodiment, and a computer readable storage medium embodiment, which are similar to a method embodiment, so that description is relatively simple, and relevant content in reading apparatus embodiments, and computer readable storage medium embodiments is referred to in the description of the method embodiment.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In the 30 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable GATE ARRAY, FPGA)) is an integrated circuit whose logic functions are determined by user programming of the device. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented with "logic compiler (logic compiler)" software, which is similar to the software compiler used in program development and writing, and the original code before being compiled is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but HDL is not just one, but a plurality of kinds, such as ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language), and VHDL (Very-High-SPEED INTEGRATED Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application SPECIFIC INTEGRATED Circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each unit may be implemented in the same piece or pieces of software and/or hardware when implementing the embodiments of the present specification.

One skilled in the relevant art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-readable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising at least one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

One or more embodiments of the present specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The foregoing description is by way of example only and is not intended to limit the present disclosure. Various modifications and changes may occur to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. that fall within the spirit and principles of the present document are intended to be included within the scope of the claims of the present document.

Claims (14)

1. A resource data recommendation processing method comprises the following steps:

carrying out data conversion processing on project related data of resource projects to obtain converted project data;

constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata;

And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

2. The resource data recommendation processing method according to claim 1, wherein the performing data conversion processing on the item-related data of the resource item to obtain converted item data includes:

Filtering the project related data to obtain filtered project data;

performing data annotation on the filtered item data to obtain annotated item data;

and carrying out data conversion on the marked item data to obtain converted item data.

3. The resource data recommendation processing method according to claim 2, wherein the filtering the project-related data to obtain filtered project data comprises:

identifying noise data contained in the project related data, and deleting the noise data from the project related data;

Analyzing the deleted project related data, deleting the access invalid data obtained by analysis, and obtaining the filtered project data.

4. The method for recommending and processing resource data according to claim 2, wherein the step of performing data annotation on the filtered item data to obtain annotated item data comprises the steps of:

Performing word segmentation processing on the filtered project data to obtain project keywords;

and marking type labels based on the word types of the item keywords, and obtaining the marked item data marked with the type labels.

5. The resource data recommendation processing method according to claim 1, wherein the step of performing data conversion processing on item-related data of resource items, before the step of obtaining converted item data, further comprises:

Determining a plurality of data sources of the resource project according to the recommended scene category of the resource project, and acquiring project data of the resource project from the plurality of data sources;

And carrying out de-duplication processing on the acquired project data to acquire the project related data.

6. The resource data recommendation processing method according to claim 1, wherein the recommendation data configuration is generated by configuring a recommendation data template displayed on a recommendation data configuration page;

The recommended data configuration includes at least one of: data attention level configuration, language type configuration and data visualization configuration.

7. The resource data recommendation processing method according to claim 6, wherein the recommendation data generation performed by the recommendation data generation model comprises:

Generating a recommended data text according to the data attention level configuration and/or the language type configuration and the conversion project data;

And extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visual configuration.

8. The resource data recommendation processing method according to claim 1, the constructing recommendation input data according to the conversion item data and the recommendation data configuration of the resource item, comprising:

Analyzing the conversion project data and the recommended data configuration;

And filling the analysis result into an input data template of the recommended data generation model, and taking the input data file obtained after filling as the recommended input data.

9. The resource data recommendation processing method according to claim 1, the constructing recommendation data of the resource item based on the recommendation metadata, comprising:

performing data assembly on the recommendation metadata according to the delivery equipment parameters of the recommendation channel to obtain the recommendation data;

Or alternatively

And carrying out data assembly on the recommendation metadata according to a data assembly strategy corresponding to the type of the delivery equipment of the recommendation channel to obtain the recommendation data.

10. The resource data recommendation processing method according to claim 1, wherein the recommending processing of the recommended data to the recommendation channel of the resource item comprises:

recommending the recommendation data to the delivery equipment in the delivery equipment list of the recommendation channel by the delivery equipment, so that the recommendation data is displayed on the delivery equipment.

11. The resource data recommendation processing method according to claim 1, wherein the recommendation data generation model is obtained by:

fine tuning the pre-training model based on a pre-marked project data set to obtain an intermediate model;

testing the intermediate model based on a test data set, and performing parameter adjustment on the intermediate model according to a test result to obtain the recommended data generation model;

The pre-training model is obtained by carrying out model training on a model to be trained based on corpus samples in a corpus.

12. A resource data recommendation processing apparatus comprising:

the data conversion module is configured to perform data conversion processing on project related data of the resource project to obtain converted project data;

the data generation module is configured to construct recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, input the recommendation input data into a recommendation data generation model to generate recommendation data, and obtain recommendation metadata;

And the recommendation processing module is configured to construct recommendation data of the resource items based on the recommendation metadata and conduct recommendation processing of the recommendation data to recommendation channels of the resource items.

13. A resource data recommendation processing apparatus comprising:

a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to:

carrying out data conversion processing on project related data of resource projects to obtain converted project data;

constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource projects, inputting the recommendation input data into a recommendation data generation model to generate recommendation data, and obtaining recommendation metadata;

And constructing recommendation data of the resource items based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource items.

14. A computer readable storage medium storing computer executable instructions which, when executed, implement the steps of the method of claim 1.