Resource data recommendation processing

Abstract

Embodiments of the present description provide a resource data recommendation processing method and apparatus. The resource data recommendation processing method comprises: in a data recommendation process for a resource project, starting with project-related data of the resource project, transforming the project-related data into transformed project data; constructing recommendation input data on the basis of the transformed project data and a recommendation data configuration of the resource project, and inputting the recommendation input data into a recommendation data generation model for recommendation data generation to obtain recommendation metadata (S204); and further, assembling recommendation data of the resource project on the basis of the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource project (S206), so as to achieve recommendation data generation and recommendation processing for the resource project.

Description

Resource data recommendation processing Technical Field

[0001] This document relates to the field of data processing technology, and in particular to methods and devices for resource data recommendation processing. Background Art

[0002] With the continuous development and promotion of the Internet, the application scope of online services provided by the Internet has become increasingly wider and has gradually covered most users. In this case, various forms of online service scenarios have emerged, such as the distribution of marketing materials for project products online. The distribution of marketing materials not only needs to demonstrate the performance or potential of the project products themselves, but also needs to present the revenue or income of the project products in an easy-to-understand manner. This is a big challenge for many project product providers. Summary of the Invention

[0003] One or more embodiments of the present specification provide a resource data recommendation processing method, including: performing data conversion processing on project-related data of a resource project to obtain converted project data; constructing recommendation input data based on the converted project data and the recommended data configuration of the resource project, and inputting the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; constructing the recommended data of the resource project based on the recommendation metadata, and performing recommendation processing on the recommended data to a recommendation channel of the resource project.

[0004] One or more embodiments of the present specification provide a resource data recommendation processing device, including: a data conversion module, configured to perform data conversion processing on project-related data of a resource project to obtain converted project data; a data generation module, configured to construct recommendation input data based on the converted project data and the recommended data configuration of the resource project, and input the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; a recommendation processing module, configured to assemble the recommendation data of the resource project based on the recommendation metadata, and perform recommendation processing of the recommendation data to a recommendation channel of the resource project.

[0005] One or more embodiments of the present specification provide a resource data recommendation processing device, comprising a processor and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, cause the processor to: perform data conversion processing on project-related data of a resource project to obtain converted project data; construct recommendation input data based on the converted project data and the recommendation data configuration of the resource project, and input the recommendation input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; assemble recommendation data for the resource project based on the recommendation metadata, and perform recommendation processing on the recommendation data to a recommendation channel for the resource project.

[0006] One or more embodiments of the present specification provide a computer-readable storage medium for storing computer-executable instructions, which implement the following process when executed: performing data conversion processing on project-related data of a resource project to obtain converted project data; constructing recommendation input data based on the converted project data and the recommended data configuration of the resource project, and inputting the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; constructing the recommendation data of the resource project based on the recommendation metadata, and recommending the recommendation data to a recommendation channel of the resource project. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0008] FIG1 is a schematic diagram of an implementation environment of a resource data recommendation processing method provided by one or more embodiments of this specification.

[0009] FIG2 is a processing flow chart of a resource data recommendation processing method provided by one or more embodiments of this specification.

[0010] FIG3 is a processing flow chart of a model training process provided by one or more embodiments of this specification.

[0011] FIG4 is a processing flow chart of a resource data recommendation processing method applied to a marketing recommendation scenario provided by one or more embodiments of this specification.

[0012] FIG5 is a processing flow chart of a resource data recommendation processing method applied to an equity project recommendation scenario provided by one or more embodiments of this specification.

[0013] FIG6 is a schematic diagram of an embodiment of a resource data recommendation processing device provided by one or more embodiments of this specification.

[0014] FIG7 is a schematic diagram of the structure of a resource data recommendation processing device provided by one or more embodiments of this specification. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0016] The resource data recommendation processing method provided in one or more embodiments of this specification can be applied to the implementation environment of resource project recommendation. Referring to Figure 1, the implementation environment at least includes: a server 101 for acquiring data, processing data, and recommending data for resource projects, a recommendation data generation model 102 for generating recommendation data based on input of resource projects from the server 101, and a delivery terminal 103 for receiving data recommendations from the server 101.

[0017] The server 101 may be a single server, a server cluster consisting of several servers, or one or more cloud servers in a cloud computing platform; the recommendation data generation model 102 may be a generative model obtained by fine-tuning a pre-trained model, which generates recommendation metadata based on data input recommendations; the delivery terminal 103 may be a mobile phone, a computer, a tablet computer, an e-book reader, a device for information interaction based on VR (Virtual Reality) technology, an in-vehicle terminal, an IoT device, a wearable smart device, a laptop computer, a desktop computer, an advertising terminal, and the like.

[0018] In this implementation environment, during the process of recommending data for resource items, the server 101 performs data conversion processing on the project-related data of the recommended resource items, constructs recommendation input data for input into the recommendation data generation model 102 based on the converted project data obtained from the conversion processing and the pre-configured recommendation data configuration of the resource items, and inputs the recommendation input data into the recommendation data generation model 102 to generate corresponding recommendation metadata, further organizes recommendation data for the resource items based on the recommendation metadata, and performs recommendation processing on the recommendation data to the recommendation channel pre-configured for the resource items, thereby recommending the recommendation data of the resource items to the corresponding delivery terminal 103 of the pre-configured recommendation channel.

[0019] One or more embodiments of a resource data recommendation processing method provided in this specification are as follows.

[0020] 2 , the resource data recommendation processing method provided in this embodiment specifically includes steps S202 to S206 .

[0021] Step S202: performing data conversion processing on the project-related data of the resource project to obtain converted project data.

[0022] The resource projects described in this embodiment can be projects for resource management, and the managed resources can be financial resources, equity assets or virtual resources. Accordingly, the resource projects can be fund management projects, equity asset management projects or virtual resource management projects; among them, fund management projects include financial management projects, equity asset management projects include equity asset management projects under asset types that can be used for trading (funds, stocks, bonds); virtual resource management projects include coupons, points, etc.

[0023] The project-related data of the resource project includes data related to the resource project, data related to the project field or project classification of the resource project, data related to the recommendation of the resource project, and / or data related to the project rights and interests of the resource project.

[0024] For example, data related to resource projects may include relevant data on the current resource project's manager or management personnel, and may also include data related to the current resource's release time, management cycle, project indicators, etc.; data related to the project field of the resource project may be news articles, analysis reports, market comments, financial blogs, etc. related to equity assets; data related to the recommendation of resource projects, and data related to the behavior of the target user group of equity assets; data related to the project equity of the resource project, and data related to the historical equity indicators of the resource project, etc.

[0025] During specific implementation, in the process of data recommendation for resource projects, in order to enable the data recommendation for resource projects to reflect the current situation of the resource projects in a timely manner, the project-related data of the resource projects can be obtained in real time, so as to ensure the timeliness of the data recommendation of the resource projects; further, in order to improve the diversity and comprehensiveness of data recommendation, in the process of obtaining the project-related data of the resource projects, the project-related data of the resource projects are obtained from multiple data sources. Specifically, in an optional implementation manner of this embodiment, before performing data conversion processing on the project-related data of the resource projects, the project-related data of the resource projects are obtained in the following manner: multiple data sources of the resource projects are determined according to the recommendation scenario category of the resource projects, and the project data of the resource projects are obtained from the multiple data sources; the obtained project data are deduplicated to obtain the project-related data.

[0026] Among them, the multiple data sources of resource projects include: a data source of data related to the resource projects, a data source of data related to the project field or project classification of the resource projects, a data source of data related to the recommendation of the resource projects, and / or a data source of data related to the project rights and interests of the resource projects.

[0027] During specific implementation, in the process of converting the project-related data of a resource project into converted project data, an optional implementation manner provided by this embodiment performs data conversion processing on the project-related data of the resource project to obtain converted project data, including: filtering the project-related data to obtain filtered project data; data labeling the filtered project data to obtain labeled project data; and data conversion on the labeled project data to obtain the converted project data.

[0028] 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 data annotation of the project-related data and data conversion of the obtained annotated project data.

[0029] Specifically, in the process of filtering project-related data, this embodiment filters the project-related data from two filtering dimensions: noise data filtering and invalid data filtering, so as to improve the accuracy of filtering the project-related data. For example, in an optional implementation provided by this embodiment, filtering the project-related data to obtain filtered project data includes: identifying noise data contained in the project-related data, deleting the noise data from the project-related data; parsing the deleted project-related data, and deleting invalid access data obtained by parsing to obtain the filtered project data. Invalid access data can be links that are trigger invalid or trigger failed, etc.

[0030] 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 data labeled, so as to help the subsequent recommendation data generation model to understand the converted project data more accurately and effectively based on the type label obtained by the data labeling. In an optional implementation provided by this embodiment, the filtered project data is data labeled to obtain labeled project data, including: performing word segmentation processing on the filtered project data to obtain project keywords; performing type label labeling based on the word type of the project keyword to obtain the labeled project data labeled with the type label.

[0031] Step S204 : constructing recommendation input data according to the conversion project data and the recommendation data configuration of the resource project, and inputting the recommendation input data into a recommendation data generation model to generate recommendation data, thereby obtaining recommendation metadata.

[0032] In this embodiment, during the process of data recommendation for resource projects, the data recommendation for resource projects can be configured accordingly. The different requirements of different resource projects for data recommendation can be reflected through configuration, so as to achieve personalized data recommendation at the resource project granularity during the data recommendation process for resource projects. The recommended data configuration refers to the pre-configured data requirements for data recommendation for resource projects.

[0033] During specific implementation, recommended data configuration can be generated and configured through the recommended data configuration page, allowing for intuitive and convenient configuration. Furthermore, to enhance configuration flexibility and convenience, recommended data templates can be configured on the recommended data configuration page. Configuration can then be performed by editing the recommended data templates. Specifically, recommended data configuration includes at least one of the following: data attention level configuration, voice type configuration, and data visualization configuration.

[0034] Among them, data focus level configuration refers to the configuration information of the focus content generated after marking the focus content in the data recommendation process of the resource project. For example, if you want to focus on the funding indicators of the fund management project, you can mark the focus funding indicators.

[0035] Voice type configuration refers to the configuration information generated after configuring the voice or style of data recommendation for resource projects. For example, in the process of recommending data for a fund management project, in order to invite users to join the fund management project, the voice of the recommended data can be configured to a more polite invitation voice. Another example is content style configuration, which configures specific content in the recommended data as a content style.

[0036] Data visualization configuration refers to the configuration information generated after configuring the data visualization form recommended for resource projects. For example, in the data recommendation process for fund management projects, the specified data is configured as a chart configuration for display in the form of a chart.

[0037] In actual applications, based on the conversion project data as the basis for data generation and the recommended data configuration of the resource project as the requirement for data generation, the recommended data generation model generates recommended data based on the conversion project data and the recommended data configuration of the resource project. Here, the recommended data generation model for generating recommended data may have some restrictions on the format of the input data, such as the requirement for input data to be an input prompt file.

[0038] To this end, recommended input data is constructed based on the recommended data configuration of the conversion project data and the resource project, so that the recommended input data is used as the input of the recommendation data generation model. Specifically, in an optional implementation provided by this embodiment, recommended input data is constructed based on the recommended data configuration of the conversion project data and the resource project, including: parsing the conversion project data and the recommended data configuration; filling the parsing results into the input data template of the recommendation data generation model, and using the input data file obtained after filling as the recommended input data.

[0039] For example, the conversion project data and the recommended data configuration are parsed to obtain the parsed content of the conversion project data and the parsed content of the recommended data configuration. According to the prompt (prompt word) template of the recommended data generation model, the parsed content of the recommended data configuration is added to the question part of the prompt template, and the parsed content of the conversion project data after parsing is added to the data part of the prompt template to obtain the prompt file for inputting the recommended data generation model.

[0040] It should be noted that in actual applications, there may be situations where the recommendation data generation model does not set data input restrictions or rules, or the conversion project data conforms to the data input restrictions or rules of the recommendation data generation model. In this case, the recommended data configuration of the conversion project data and resource items can be directly input into the recommendation data generation model to generate recommended data and obtain recommended metadata, that is: the above-mentioned process of constructing recommended input data based on the recommended data configuration of the conversion project data and resource items, and inputting the recommended input data into the recommendation data generation model to generate recommended data can be replaced by inputting the recommended data configuration of the conversion project data and resource items into the recommendation data generation model to generate recommended data.

[0041] In specific implementations, based on the recommended input data obtained from the conversion project data and the recommended data configuration of the resource project, this recommended input data is fed into the recommended data generation model to generate recommended data and obtain recommendation metadata. Recommendation metadata refers to the data recommendations generated by the recommended data generation model based on the conversion project data and the recommended data configuration. This data recommendation content requires further data construction before it can be recommended, hence the name recommendation metadata.

[0042] The recommendation data generation model refers to a data generation model obtained through further training or fine-tuning of a pre-trained model. The model input includes the recommended data configuration for the conversion project data and resource items. The trained or fine-tuned data generation model is capable of generating recommended data based on the recommended data configuration for the conversion project data and resource items, obtaining and outputting recommendation metadata. A pre-trained model refers to a pre-trained natural language model. A pre-trained model can utilize a neural network architecture with a large number of parameters. Pre-trained models can utilize pre-trained large language models (LLMs), such as conversational interaction models in the conversational interaction field or generative models in the content generation field.

[0043] As mentioned above, the recommended data configuration includes at least one of the data attention level configuration, the voice type configuration, and the data visualization configuration. Here, taking the recommended data configuration including the data attention level configuration and the data visualization configuration as an example, the process of generating recommended data by the recommended data generation model is specifically explained.

[0044] For example, the recommendation data generation model performs recommendation data generation, including: generating recommendation data text based on the conversion project data according to the data attention level configuration; extracting visualization data from the conversion project data, and generating a visualization data component based on the visualization data and the data visualization configuration.

[0045] In addition, when the recommendation data configuration includes a voice type configuration and a data visualization configuration, the recommendation data generation performed by the recommendation data generation model includes: generating recommendation data text according to the conversion project data in accordance with the voice type configuration; extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visualization configuration; or, when the recommendation data configuration includes a data attention level configuration, a voice type configuration and a data visualization configuration, the recommendation data generation performed by the recommendation data generation model includes: generating recommendation data text according to the conversion project data in accordance with the data attention level configuration and the voice type configuration; extracting visual data in the conversion project data, and generating a visual data component based on the visual data and the data visualization configuration.

[0046] In this embodiment, the recommendation data generation model is obtained by further training or fine-tuning the pre-trained model. The input of the recommendation data generation model includes the recommended data configuration of the conversion project data and the resource project. The trained or fine-tuned recommendation data generation model can generate recommendation data based on the recommended data configuration of the conversion project data and the resource project, obtain recommendation metadata and output it. In an optional implementation provided by this embodiment, the recommendation data generation model is obtained in the following manner: fine-tuning the pre-trained model based on a pre-labeled project data set to obtain an intermediate model; testing the intermediate model based on a test data set, adjusting the parameters of the intermediate model according to the test results, and obtaining the recommendation data generation model.

[0047] Among them, the pre-trained model can also be obtained by training the model to be trained based on the corpus samples in the corpus.

[0048] For example, as shown in FIG3 , the training process of the recommendation data generation model specifically includes the following steps.

[0049] Step S302: Data Acquisition. Data acquisition is performed from multiple data sources for the resource project, specifically including: acquiring relevant data on the current resource project's manager or management personnel; data related to the current resource project's release time, management cycle, project indicators, etc.; news articles, analysis reports, market reviews, financial blogs, etc. related to the resource project; behavioral data related to the target user group of the resource project; and data related to the resource project's historical equity indicators.

[0050] Step S304: Data preprocessing. First, identify the noise data contained in the acquired data and delete the noise data from the acquired data. Then, parse the deleted data and delete invalid access data such as links with invalid or failed triggers. Second, label the deleted data and perform data conversion on the labeled data to obtain sample data.

[0051] Step S306: Model pre-training. A model architecture (e.g., Transformers) is selected, and a model to be trained is constructed based on the selected architecture. The model to be trained is trained using sample data, and a pre-trained model is obtained after training. Training tasks can be set during the training process, such as learning context and relationships between vocabulary.

[0052] Step S308: Fine-tune the pre-trained model. Using pre-labeled resource project data, a specific dataset for this field is recommended. Fine-tune the pre-trained model to adjust its parameters and obtain a recommended data generation model. Specific data generation tasks can be set during the fine-tuning process, such as generating marketing copy or resource management recommendations.

[0053] Step S310: Model testing: The fine-tuned pre-trained model is tested using a test dataset independent of the specific dataset, and the model parameters of the fine-tuned pre-trained model are optimized based on the test results to obtain a recommendation data generation model.

[0054] Step S312: Model optimization and update: During the actual application of the recommendation data generation model, the parameters of the recommendation data generation model may be further optimized and adjusted based on the feedback or evaluation results of the recommendation metadata of the recommendation data generation model.

[0055] Step S206 : constructing recommendation data for the resource item based on the recommendation metadata, and performing recommendation processing on the recommendation data to a recommendation channel for the resource item.

[0056] In a specific implementation scenario, after obtaining the recommendation metadata of a resource project through a recommendation data generation model, recommendation data of the resource project is assembled based on the recommendation metadata to obtain recommendation data for recommendation to a recommendation channel of the resource project, and the recommendation data is processed to be recommended to the recommendation channel of the resource project.

[0057] In an optional implementation provided by this embodiment, constructing the recommendation data of the resource item based on the recommendation metadata includes: assembling the recommendation metadata according to the delivery device parameters of the recommendation channel to obtain the recommendation data; or assembling the recommendation metadata according to the data assembly strategy corresponding to the delivery device type of the recommendation channel to obtain the recommendation data.

[0058] In actual applications, the recommended channels for resource items can be pre-configured, and the list of delivery devices for the resource items in the configured recommended channels can be further configured. Based on this, automated data recommendation processing can be performed based on the pre-configured list of delivery devices for the recommended channels. Specifically, in an optional implementation provided by this embodiment, the recommended data is recommended to the recommended channel of the resource item, including: recommending the recommended data to the delivery device in the delivery device list of the recommended channel, so as to display the recommended data on the delivery device.

[0059] To sum up, the resource data recommendation processing method provided in this embodiment obtains the project-related data of the resource project in real time during the data recommendation process for the resource project, so that the obtained project-related data can promptly reflect the current situation of the resource project, thereby ensuring the timeliness of the data recommendation of the resource project; on this basis, the project-related data of the resource project is subjected to data conversion processing to obtain converted project data, and recommendation input data is constructed according to the converted project data and the pre-configured recommended data configuration of the resource project as the input of the recommendation data generation model, thereby reflecting the personalization of data recommendation through the recommendation data configuration, and improving the flexibility and convenience of data recommendation. Thereafter, the recommendation input data is input into the recommendation data generation model to generate recommendation data, obtain recommendation metadata, and construct the recommendation data of the resource project based on the recommendation metadata, so that the constructed recommendation data can adapt to the data recommendation requirements of the pre-configured recommendation channel of the resource project, and finally the recommended data is recommended to the recommendation channel of the resource project, thereby realizing efficient and fast automated data recommendation for resource projects.

[0060] The following takes the application of a resource data recommendation processing method provided by this embodiment in a marketing recommendation scenario as an example, and combines Figure 4 to further illustrate the resource data recommendation processing method provided by this embodiment. Referring to Figure 4, the resource data recommendation processing method applied to the marketing recommendation scenario specifically includes the following steps.

[0061] Step S402 : determining multiple data sources of the resource item according to the recommended scenario category of the resource item, and acquiring project data of the resource item from the multiple data sources.

[0062] Step S404: filter the acquired project data to obtain filtered project data.

[0063] Step S406: annotate the filtered item data to obtain annotated item data.

[0064] Step S408: performing data conversion on the marked item data to obtain converted item data.

[0065] Step S410 , parsing the conversion project data and the recommended data configuration of the resource project, and filling the parsing result into the input data template to obtain an input data file.

[0066] Step S412: input the input data file into the recommendation data generation model to generate marketing recommendation data and obtain marketing recommendation metadata.

[0067] Step S414 , assembling the marketing recommendation metadata according to the delivery device parameters of the recommended channel of the resource item to obtain marketing recommendation data.

[0068] Step S416: Recommend the marketing recommendation data to the recommendation channel of the resource item.

[0069] It should be noted that any one of steps S402 to S416 or any combination of multiple steps can be replaced by the corresponding technical means provided in the above steps S202 to S206 according to the needs of implementation and deployment, and will not be described one by one here.

[0070] The following takes the application of a resource data recommendation processing method provided by this embodiment in an equity project recommendation scenario as an example, and combines Figure 5 to further illustrate the resource data recommendation processing method provided by this embodiment. Referring to Figure 5, the resource data recommendation processing method applied to the equity project recommendation scenario specifically includes the following steps.

[0071] Step S502: perform word segmentation processing on the project-related data of the equity project to obtain project keywords.

[0072] Step S504: perform type tagging based on the word type of the project keyword to obtain the tagged project data tagged with the type tag.

[0073] Step S506: performing data conversion on the marked item data to obtain converted item data.

[0074] Step S508 : constructing recommended input data according to the converted project data and the voice type configuration and data visualization configuration of the equity project.

[0075] Step S510: input the recommendation input data into the recommendation data generation model to generate recommendation data, and obtain recommendation data text and visualization data components.

[0076] Optionally, the recommendation data generation model performs recommendation data generation, including: generating recommendation data text based on the converted project data according to the voice type configuration; extracting visual data from the converted project data, and generating visual data components based on the visual data and the data visualization configuration.

[0077] Step S512: assemble recommendation data based on the recommendation data text and the visual data component, and perform recommendation processing on the recommendation data to the recommendation channel of the equity project.

[0078] It should be noted that any one of steps S502 to S512 or any combination of multiple steps can be replaced by the corresponding technical means provided in the above steps S202 to S206 according to the needs of implementation and deployment, and will not be described one by one here.

[0079] An embodiment of a resource data recommendation processing device provided in this specification is as follows.

[0080] In the above-mentioned embodiment, a resource data recommendation processing method is provided, and correspondingly, a resource data recommendation processing device is also provided, which will be described below with reference to the accompanying drawings.

[0081] 6 , which shows a schematic diagram of an embodiment of a resource data recommendation processing device provided by this embodiment.

[0082] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0083] This embodiment provides a resource data recommendation processing device, which includes: a data conversion module 602, which is configured to perform data conversion processing on project-related data of a resource project to obtain converted project data; a data generation module 604, which is configured to construct recommendation input data based on the converted project data and the recommended data configuration of the resource project, and input the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; a recommendation processing module 606, which is configured to assemble the recommendation data of the resource project based on the recommendation metadata, and perform recommendation processing of the recommendation data to the recommendation channel of the resource project.

[0084] An embodiment of a resource data recommendation processing device provided in this specification is as follows.

[0085] Corresponding to the resource data recommendation processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a resource data recommendation processing device, which is used to execute the resource data recommendation processing method provided above. Figure 7 is a structural schematic diagram of a resource data recommendation processing device provided by one or more embodiments of this specification.

[0086] This embodiment provides a resource data recommendation processing device, as shown in Figure 7. The resource data recommendation processing device may have relatively large differences due to different configurations or performances, and may include one or more processors 701 and memory 702. The memory 702 may store one or more storage applications or data. Among them, the memory 702 can be a temporary storage or a persistent storage. The application stored in the memory 702 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the resource data recommendation processing device. Furthermore, the processor 701 can 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, etc.

[0087] In a specific embodiment, a 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 is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: performing data conversion processing on project-related data of a resource project to obtain converted project data; constructing recommendation input data based on the converted project data and the recommended data configuration of the resource project, and inputting the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; organizing the recommendation data of the resource project based on the recommendation metadata, and performing recommendation processing of the recommendation data to the recommendation channel of the resource project.

[0088] An embodiment of a computer-readable storage medium provided in this specification is as follows.

[0089] Corresponding to the resource data recommendation processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0090] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which implement the following process when executed: performing data conversion processing on project-related data of a resource project to obtain converted project data; constructing recommendation input data based on the converted project data and the recommended data configuration of the resource project, and inputting the recommended input data into a recommendation data generation model to generate recommendation data to obtain recommendation metadata; constructing the recommendation data of the resource project based on the recommendation metadata, and recommending the recommendation data to the recommendation channel of the resource project.

[0091] It should be noted that the embodiment of a computer-readable storage medium in this specification and the embodiment of a resource data recommendation processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0092] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For example, the device embodiment, equipment embodiment and computer-readable storage medium embodiment are similar to the method embodiment, so the description is relatively simple. For relevant content in the device embodiment, equipment embodiment and computer-readable storage medium embodiment, please refer to the partial description of the method embodiment.

[0093] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] In the 1930s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, 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), etc. The most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0095] The controller can be implemented in any suitable manner. For example, the controller can take the form of 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: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0096] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, 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.

[0097] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0098] Those skilled in the art will appreciate that one or more embodiments of this specification may be provided as a method, system, or computer program product. Thus, one or more embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0100] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0102] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0103] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0104] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising at least one ..." does not exclude the presence of additional identical elements in the process, method, commodity, or apparatus comprising the element.

[0106] One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0107] The foregoing description is merely an example of the present invention and is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of the claims herein.

Claims

1. A resource data recommendation processing method, comprising: Perform data conversion 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 project, and inputting the recommendation input data into a recommendation data generation model to generate recommendation data, thereby obtaining recommendation metadata; Recommendation data for the resource item is constructed based on the recommendation metadata, and recommendation processing of the recommendation data is performed on a recommendation channel for the resource item.

2. The resource data recommendation processing method according to claim 1, wherein the step of converting the project-related data of the resource project to obtain the converted project data comprises: Filtering the project-related data to obtain filtered project data; Performing data labeling on the filtered item data to obtain labeled item data; Perform data conversion on the marked item data to obtain the converted item data.

3. The resource data recommendation processing method according to claim 2, wherein 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; The deleted project-related data is parsed, and the invalid access data obtained by the parsing is deleted to obtain the filtered project data.

4. The resource data recommendation processing method according to claim 2, wherein the step of labeling the filtered item data to obtain the labeled item data comprises: Perform word segmentation processing on the filtered project data to obtain project keywords; Type labeling is performed based on the word type of the project keyword to obtain the labeled project data labeled with the type label.

5. The resource data recommendation processing method according to claim 1, wherein before the step of converting the project-related data of the resource project and obtaining the converted project data is performed, the method further comprises: determining a plurality of data sources of the resource item according to the recommended scenario category of the resource item, and acquiring the item data of the resource item from the plurality of data sources; Deduplication processing is performed on the acquired project data to obtain the project-related data.

6. The resource data recommendation processing method according to claim 1, wherein the recommended data configuration is generated by configuring a recommended data template displayed on a recommended data configuration page; The recommended data configuration includes at least one of the following: data attention level configuration, voice type configuration, and data visualization configuration.

7. The resource data recommendation processing method according to claim 6, wherein the recommendation data generation model generates recommendation data, comprising: generating a recommended data text based on the converted project data according to the data attention level configuration and / or the voice type configuration; Visualization data in the conversion project data is extracted, and a visualization data component is generated based on the visualization data and the data visualization configuration.

8. The resource data recommendation processing method according to claim 1, wherein the step of constructing the recommendation input data based on the conversion project data and the recommended data configuration of the resource project comprises: parsing the conversion project data and the recommended data configuration; The parsing result is filled into the input data template of the recommendation data generation model, and the input data file obtained after filling is used as the recommendation input data.

9. The resource data recommendation processing method according to claim 1, wherein the step of constructing the recommendation data of the resource item based on the recommendation metadata comprises: Assembling the recommendation metadata according to the delivery device parameters of the recommendation channel to obtain the recommendation data; or, The recommendation metadata is assembled according to the data assembly strategy corresponding to the delivery device type of the recommendation channel to obtain the recommendation data.

10. The resource data recommendation processing method according to claim 1, wherein the step of performing the recommendation processing on the recommendation channel of the resource item comprises: The recommended data is recommended to the delivery device in the delivery device list of the recommendation channel, so as to display the recommended data on the delivery device.

11. The resource data recommendation processing method according to claim 1, wherein the recommendation data generation model is obtained by: Fine-tune the pre-trained model based on the pre-labeled project dataset to obtain an intermediate model; Testing the intermediate model based on a test data set, adjusting parameters of the intermediate model according to the test results, and obtaining the recommendation data generation model; in, The pre-trained model is obtained by training the model to be trained based on corpus samples in the corpus.

12. A resource data recommendation processing device, comprising: A data conversion module is configured to perform data conversion processing on project-related data of a resource project to obtain converted project data; a data generation module 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 generation model to generate recommendation data, thereby obtaining recommendation metadata; The recommendation processing module is configured to assemble 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.

13. A resource data recommendation processing device, comprising: processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: Perform data conversion 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 project, and inputting the recommendation input data into a recommendation data generation model to generate recommendation data, thereby obtaining recommendation metadata; Recommendation data for the resource item is constructed based on the recommendation metadata, and recommendation processing of the recommendation data is performed on a recommendation channel for the resource item.

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

Images