Data set processing method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to a data set processing method and device, electronic equipment and storage medium. The method comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; determining a first associated multimedia set of each of the plurality of target data; performing recommendation processing on the plurality of target data based on the multimedia candidate set and the first associated multimedia set to obtain first recommendation feedback information of the multimedia candidate set; and determining an attribute matching result corresponding to the target data set based on the first recommendation feedback information. According to the technical scheme provided by the present disclosure, the accuracy of the attribute matching result corresponding to the data set can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of Internet application technology, and in particular to a dataset processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of the internet, multimedia recommendation services have attracted much attention. In the recommendation process, accurately selecting datasets for recommendation is fundamental to improving recommendation effectiveness. Related technologies generally involve configuring attribute information for the dataset to describe it, thereby providing a basis for multimedia recommendations and improving recommendation performance. However, currently, the attribute information configured for the dataset mainly relies on experience-based settings, resulting in insufficient accuracy and consequently, suboptimal recommendation results. Summary of the Invention

[0003] This disclosure provides a dataset processing method, apparatus, electronic device, and storage medium. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a dataset processing method is provided, comprising:

[0005] Obtain the target dataset to be tested and the multimedia candidate set corresponding to the target dataset. The target dataset includes multiple target datasets, and the multimedia candidate set consists of preset multimedia datasets that match the dataset attribute information of the target dataset.

[0006] Determine the first associated multimedia set for each of the plurality of target data;

[0007] Based on the multimedia candidate set and the first associated multimedia set, recommendation processing is performed on the multiple target data to obtain the first recommendation feedback information of the multimedia candidate set;

[0008] Based on the first recommendation feedback information, the attribute matching result corresponding to the target dataset is determined.

[0009] In one possible implementation, the step of performing recommendation processing on the plurality of target data based on the multimedia candidate set and the first associated multimedia set to obtain first recommendation feedback information for the multimedia candidate set includes:

[0010] Obtain a set of multimedia to be matched that matches the data attribute information of each of the multiple target data;

[0011] If the multimedia set to be matched matches the multimedia candidate set, recommendation processing is performed on the multiple target data based on the multimedia candidate set and the first associated multimedia set to obtain the first recommendation feedback information of the multimedia candidate set.

[0012] In one possible implementation, the step of performing recommendation processing on the plurality of target data based on the multimedia candidate set and the first associated multimedia set to obtain first recommendation feedback information for the multimedia candidate set includes:

[0013] The candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set are sorted to filter out the multimedia set to be recommended.

[0014] Based on the set of multimedia to be recommended, the multiple target data are recommended to obtain the display information of the candidate multimedia and the statistical information of the candidate multimedia being subjected to preset operations.

[0015] Based on the displayed information and the statistical information, the first recommendation feedback information is obtained.

[0016] In one possible implementation, the method further includes:

[0017] Obtain the dataset to be recommended and the second associated multimedia set of each of the multiple data to be recommended in the dataset to be recommended;

[0018] Based on the multimedia candidate set and the second associated multimedia set, the multiple data to be recommended are processed to obtain the second recommendation feedback information of the multimedia candidate set;

[0019] The step of determining the attribute matching result corresponding to the target dataset based on the first recommendation feedback information includes:

[0020] Based on the first recommendation feedback information and the second recommendation feedback information, the attribute matching result corresponding to the target dataset is determined.

[0021] In one possible implementation, obtaining the target dataset to be tested includes:

[0022] Obtain multiple initial datasets;

[0023] The initial dataset to be tested is determined from the plurality of initial datasets;

[0024] Obtain activity information corresponding to multiple initial data points in the initial dataset to be tested;

[0025] Based on the activity information, multiple initial data in the initial dataset to be tested are filtered to obtain the target dataset.

[0026] In one possible implementation, the method further includes:

[0027] Based on the attribute matching results, an attribute matching report and the report entry information of the attribute matching report are generated;

[0028] Attribute matching record information is generated based on the dataset identifier information of the target dataset, the dataset attribute information, and the report entry information.

[0029] In one possible implementation, the target dataset is any one of a plurality of datasets, and the method further includes:

[0030] In response to a multimedia recommendation request from the terminal, attribute matching record information of the multiple datasets is sent to the terminal;

[0031] Upon detecting a request to view the target report entry information for target attribute matching record information, a target attribute matching report corresponding to the target report entry information is sent to the terminal; the target attribute matching record information is any one of the test record information of the multiple datasets.

[0032] According to a second aspect of the present disclosure, a dataset processing apparatus is provided, comprising:

[0033] The data and multimedia acquisition module is configured to acquire the target dataset to be tested and the multimedia candidate set corresponding to the target dataset. The target dataset includes multiple target datasets, and the multimedia candidate set consists of preset multimedia that matches the dataset attribute information of the target dataset.

[0034] The determination module is configured to determine a first associated multimedia set for each of the plurality of target data;

[0035] The first recommendation module is configured to perform recommendation processing on the multimedia candidate set and the first associated multimedia set to the multiple target data, and obtain the first recommendation feedback information of the multimedia candidate set.

[0036] The attribute matching result determination module is configured to determine the attribute matching result corresponding to the target dataset based on the first recommendation feedback information.

[0037] In one possible implementation, the first recommendation module includes:

[0038] The multimedia set acquisition unit is configured to acquire a multimedia set to be matched that matches the data attribute information of the plurality of target data.

[0039] The first recommendation unit is configured to perform recommendation processing on the plurality of target data based on the multimedia candidate set and the first associated multimedia set when the multimedia set to be matched matches the multimedia candidate set, thereby obtaining the first recommendation feedback information of the multimedia candidate set.

[0040] In one possible implementation, the first recommendation module includes:

[0041] The sorting unit is configured to perform sorting processing on the candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set, and to filter out the multimedia set to be recommended.

[0042] The second recommendation unit is configured to perform recommendation processing on the multiple target data based on the multimedia set to be recommended, and to obtain the display information of the candidate multimedia and the statistical information of the candidate multimedia being subjected to preset operations.

[0043] The recommendation feedback information acquisition unit is configured to obtain the first recommendation feedback information based on the display information and the statistical information.

[0044] In one possible implementation, the device further includes:

[0045] The acquisition module is configured to acquire the dataset to be recommended and the second associated multimedia set of each of the multiple datasets to be recommended in the dataset to be recommended;

[0046] The second recommendation module is configured to perform recommendation processing on the multiple data to be recommended based on the multimedia candidate set and the second associated multimedia set, and obtain the second recommendation feedback information of the multimedia candidate set.

[0047] The attribute matching result determination module is further configured to determine the attribute matching result corresponding to the target dataset based on the first recommendation feedback information and the second recommendation feedback information.

[0048] In one possible implementation, the data and multimedia acquisition module includes:

[0049] The initial dataset acquisition unit is configured to acquire multiple initial datasets.

[0050] The unit for determining the initial dataset to be tested is configured to perform the task of determining the initial dataset to be tested from the plurality of initial datasets;

[0051] The activity information acquisition unit is configured to acquire activity information corresponding to multiple initial data in the initial dataset to be tested;

[0052] The target dataset acquisition unit is configured to perform filtering processing on multiple initial data in the initial dataset to be tested based on the activity information to obtain the target dataset.

[0053] In one possible implementation, the device further includes:

[0054] The report generation module is configured to generate an attribute matching report and the report entry information of the attribute matching report based on the attribute matching results.

[0055] The test record information generation module is configured to generate attribute matching record information based on the dataset identifier information, the dataset attribute information, and the report entry information of the target dataset.

[0056] In one possible implementation, the target dataset is any one of a plurality of datasets, and the apparatus further includes:

[0057] The first sending module is configured to execute a multimedia recommendation request in response to the terminal, and send attribute matching record information of the multiple datasets to the terminal;

[0058] The second sending module is configured to execute a request to view the target report entry information that detects the target attribute matching record information, and send the target attribute matching report corresponding to the target report entry information to the terminal; the target attribute matching record information is any one of the test record information of the multiple datasets.

[0059] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method as described in any one of the first aspects above.

[0060] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided such that, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform any of the methods described in the first aspect of the present disclosure.

[0061] According to a fifth aspect of the present disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, cause a computer to perform the method described in any one of the first aspects of the present disclosure.

[0062] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects:

[0063] By recommending the multimedia candidate set and the first associated multimedia set to multiple target datasets, first recommendation feedback information of the multimedia candidate set is obtained. Based on the first recommendation feedback information, the attribute matching results of the target dataset are determined. The multimedia candidate set matches the dataset attribute information of the target dataset and is used as a targeted recall, recommended together with the first associated dataset. This can accurately test whether the target dataset matches the dataset attribute information. Furthermore, the recommendation process here is conducted online, making the first recommendation feedback information more realistic, thereby further improving the accuracy of the matching test, providing accurate reference for multimedia recommendation, and improving the recommendation effect of multimedia.

[0064] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0065] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0066] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment.

[0067] Figure 2 This is a flowchart illustrating a dataset processing method according to an exemplary embodiment.

[0068] Figure 3 This is a flowchart illustrating a method for recommending multiple target data based on a multimedia candidate set and a first associated multimedia set, according to an exemplary embodiment, to obtain first recommendation feedback information for the multimedia candidate set.

[0069] Figure 4 This is a flowchart illustrating a recommendation feedback process based on an exemplary embodiment.

[0070] Figure 5 This is a flowchart illustrating another dataset processing method according to an exemplary embodiment.

[0071] Figure 6 This is a schematic diagram of a test record according to an exemplary embodiment.

[0072] Figure 7 This is a schematic diagram of a test report according to an exemplary embodiment.

[0073] Figure 8 This is a flowchart illustrating the data set processing architecture according to an exemplary embodiment.

[0074] Figure 9This is a block diagram of a dataset processing apparatus according to an exemplary embodiment.

[0075] Figure 10 This is a block diagram illustrating an electronic device for data processing according to an exemplary embodiment. Detailed Implementation

[0076] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0077] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0078] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment, such as... Figure 1 As shown, the application environment may include server 01 and terminal 02.

[0079] In an optional embodiment, server 01 can be used for processing datasets. Specifically, server 01 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0080] In an optional embodiment, terminal 02 can display the test report in conjunction with server 01. Specifically, terminal 02 can be, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. Optionally, the operating system running on the electronic device can be, but is not limited to, Android, iOS, Linux, and Windows.

[0081] In addition, it should be noted that, Figure 1 The example shown is merely one application environment of the dataset processing method provided in this disclosure. For instance, test results can also be sent to a terminal, which can then generate and display a test report.

[0082] In the embodiments described in this specification, the server 01 and the terminal 02 can be directly or indirectly connected through wired or wireless communication, and this application does not impose any restrictions on this.

[0083] It should be noted that the following diagram illustrates one possible sequence of steps, and it is not strictly required to follow this order. Some steps can be performed in parallel without interdependence. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data used for display, training data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0084] Figure 2 This is a flowchart illustrating a dataset processing method according to an exemplary embodiment. Figure 2 As shown, the steps may include the following.

[0085] In step S201, the target dataset to be tested and the corresponding multimedia candidate set are obtained.

[0086] The target dataset may include multiple target datasets. The multimedia candidate set can be a pre-defined set of multimedia that matches the dataset attribute information of the target dataset. In other words, the target dataset to be tested has dataset attribute information, and testing the target dataset refers to testing the degree of matching between the target dataset and the dataset attribute information. The target dataset can be any one of multiple datasets. Each dataset may include dataset identification information and multiple data sets. Multiple target datasets may refer to multiple terminals or multiple user accounts; this disclosure does not limit this. As an example, the target dataset and its corresponding dataset attribute information can be as follows:

[0087] The ID of the target dataset, target data 1 to target data 100; food;

[0088] Among them, food can be the dataset attribute information of the target dataset, and the dataset attribute information can represent the data profile categories of multiple target data in the target dataset.

[0089] In practical applications, a target recommendation platform can pre-configure a multimedia candidate set for the target dataset, which can be a short video candidate set, etc. For example, a matching multimedia candidate set can be configured for the target dataset based on its dataset attribute information. Based on this, the configured multimedia candidate set that matches the dataset attribute information can be used to conduct recommendation tests on the target dataset, thereby determining whether the dataset attribute information of the target dataset is accurate and providing a reference for multimedia recommendations. The target dataset and its corresponding dataset attribute information can be uploaded to the target recommendation platform or set by the target recommendation platform. The dataset and its corresponding dataset attribute information can be saved and uploaded as a dataset package in the form of a data package. This disclosure does not impose any limitations on these aspects.

[0090] Optionally, the uploaded dataset can serve as an initial dataset. The target recommendation platform can filter multiple initial datasets to obtain the target dataset. Specifically, the filtering process can be performed based on the following steps: obtaining multiple initial datasets; determining the initial dataset to be tested from these multiple initial datasets; obtaining the activity information of multiple initial datasets in the target recommendation platform, i.e., the activity information corresponding to the multiple initial datasets; and filtering the multiple initial datasets in the initial dataset to be tested based on the activity information to obtain the target dataset. For example, filtering out initial datasets in the initial dataset to be tested that do not match the activity information to obtain the target dataset ensures that the target data in the filtered target dataset are all registered data of the target recommendation platform, ensuring that multimedia can be effectively recommended.

[0091] In step S203, the first associated multimedia set of each of the multiple target data is determined.

[0092] In the embodiments of this specification, a first associated multimedia set for each target data can be determined based on a multi-path recall method. This multi-path recall method may include intelligent recall, exploratory recall, etc., and this disclosure does not limit it.

[0093] In step S205, based on the multimedia candidate set and the first associated multimedia set, recommendation processing is performed on multiple target data to obtain the first recommendation feedback information of the multimedia candidate set.

[0094] In the embodiments of this specification, the multimedia candidate set can be used as a targeted recall and combined with the first associated multimedia set for recommendation processing. That is, the multimedia candidate set and the first associated multimedia set are pushed to multiple target datasets, thereby achieving a matching test between the target dataset and the dataset attribute information. Based on this, first recommendation feedback information of multiple candidate multimedias in the multimedia candidate set can be collected, such as the display information of the candidate multimedias.

[0095] In one possible implementation, step S205 may include: acquiring a set of multimedia to be matched that matches the data attribute information of multiple target data; and, if the set of multimedia to be matched matches the multimedia candidate set, performing recommendation processing on multiple target data based on the multimedia candidate set and the first associated multimedia set to obtain first recommendation feedback information for the multimedia candidate set, that is, recommending the multimedia candidate set and the first associated multimedia set to multiple target data to obtain first recommendation feedback information for the multimedia candidate set. In other words, the multimedia candidate set and the first associated multimedia set are only recommended to a target data if the set of multimedia to be matched that matches the data attribute information of that target data matches the multimedia candidate set. Taking a user account as an example, when a multimedia request is received from user account H, multimedia needs to be recommended to user account H to display multimedia to user account H. In this case, if user account H is a target data in the target dataset, and the set of multimedia to be matched that matches the data attribute information of user account H matches the multimedia candidate set, then the multimedia candidate set can be used as targeted recall multimedia, and recommended to user account H together with the first associated multimedia set, and recommendation feedback information can be collected. Such recommendation processing can be performed on each target data set to obtain the first recommendation feedback information of the multimedia candidate set. For example, the first recommendation feedback information of each multimedia in the multimedia candidate set within a preset time period can be statistically analyzed; the start time of this preset time period can be the start time of the target dataset test, and the duration of this preset time period can be a preset recommendation test duration, which is not limited in this disclosure. By performing recommendation processing only when the multimedia set to be matched matches the multimedia candidate set, the recommendation accuracy of the multimedia candidate set to the target dataset can be improved, thereby improving the accuracy of the attribute matching results.

[0096] Optionally, specific recommendation processing can be based on, for example... Figure 3 As shown:

[0097] In step S301, the candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set are sorted to filter out the multimedia set to be recommended.

[0098] In the embodiments of this specification, it can be as follows: Figure 4 As shown, coarse and fine sorting are performed on the candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set to obtain the sorting results. Here, the first associated multimedia set can be the intersection of multiple recalled multimedia subsets corresponding to multi-way recall.

[0099] Furthermore, based on the ranking results, a set of multimedia to be recommended can be selected from the multimedia candidate set and the first associated multimedia set. For example, a predetermined number of multimedia can be selected from the multimedia candidate set and the first associated multimedia set based on the ranking results; and a set of multimedia to be recommended can be selected from the predetermined number of multimedia based on the display resource consumption information of each multimedia. Here, the set of multimedia to be recommended corresponds to each target data.

[0100] Optionally, recommendation processing can be triggered by the client, such as when the client sends a multimedia request to the front-end server. At the start of testing, test datasets, such as the target dataset, dataset attribute information, and candidate multimedia, can be obtained from the configuration center. Data attribute information for each target dataset can also be retrieved from the database. If the user account corresponding to the client is a target dataset, the aforementioned recall and sorting operations can be performed for recommendation processing. Recommendation feedback information can then be obtained based on logs and stored in a database, which could be a Redis database.

[0101] In step S303, recommendation processing is performed on multiple target data based on the set of multimedia to be recommended, and display information of candidate multimedia and statistical information of candidate multimedia being subjected to preset operations are obtained.

[0102] In practical applications, the multimedia set to be recommended can be recommended to the corresponding target data, thereby obtaining the display information of the candidate multimedia and the statistical information of the preset operations performed on the candidate multimedia. The preset operations can be set according to actual needs, and this disclosure does not limit them; the statistical information may include quantity statistics, percentage statistics, etc., and this disclosure does not limit them.

[0103] In step S305, the first recommendation feedback information is obtained based on the displayed information and statistical information.

[0104] In the embodiments of this specification, the displayed information, statistical information, and dataset identification information of the target dataset can be associated to obtain the first recommendation feedback information. By sorting the candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set, the candidate multimedia and associated multimedia can be filtered, thereby more accurately representing the recommendation matching degree of the candidate multimedia on the target dataset, and thus effectively improving the authenticity and accuracy of the first recommendation feedback information.

[0105] In step S207, the attribute matching result corresponding to the target dataset is determined based on the first recommendation feedback information.

[0106] In the embodiments of this specification, the first recommendation feedback information can be directly used as the attribute matching result corresponding to the target dataset. Alternatively, if the first recommendation feedback information is greater than the feedback threshold, the attribute matching result corresponding to the target dataset can be determined to be a match; if the first recommendation feedback information is less than or equal to the feedback threshold, the attribute matching result corresponding to the target dataset can be determined to be a mismatch. Optionally, only target datasets with matching test results can be retained, while target datasets with mismatch test results can be filtered out. This ensures the accuracy of subsequent multimedia recommendations. The feedback threshold can include an impression quantity threshold and a statistical quantity threshold. The first recommendation feedback information being greater than the feedback threshold can mean that the impression information in the first feedback information is greater than the impression quantity threshold, and the statistical information is greater than the statistical quantity threshold.

[0107] By recommending the multimedia candidate set and the first associated multimedia set to multiple target datasets, first recommendation feedback information of the multimedia candidate set is obtained. Based on the first recommendation feedback information, the attribute matching results of the target dataset are determined. The multimedia candidate set matches the dataset attribute information of the target dataset and is used as a targeted recall, recommended together with the first associated dataset. This can accurately test whether the target dataset matches the dataset attribute information. Furthermore, the recommendation process here is conducted online, making the first recommendation feedback information more realistic, thereby further improving the accuracy of the matching test, providing accurate reference for multimedia recommendation, and improving the recommendation effect of multimedia.

[0108] Figure 5 This is a flowchart illustrating another dataset processing method according to an exemplary embodiment. Figure 5 As shown, in one possible implementation, the multimedia candidate set can also be recommended to other data outside the target dataset, thereby allowing for comparison of recommendation feedback information and improving the accuracy of test results based on this comparison. Based on this, the method may further include:

[0109] In step S501, the dataset to be recommended and the second associated multimedia set of each of the multiple datasets to be recommended in the dataset to be recommended are obtained.

[0110] In the embodiments of this specification, multiple user accounts from a multimedia recommendation platform can be obtained based on a preset method as a dataset to be recommended. This preset method may include a random method or a specified method. The specified method may refer to data outside of a specified target dataset. For the method of obtaining the second associated multimedia set, please refer to the method of obtaining the first associated multimedia set in step S203 above, and will not be repeated here.

[0111] In step S503, based on the multimedia candidate set and the second associated multimedia set, multiple data to be recommended are processed to obtain the second recommendation feedback information of the multimedia candidate set; the recommendation process can be referred to in steps S205 and S301 to S305 above, and will not be repeated here.

[0112] Accordingly, step S207 above may include:

[0113] In step S505, the attribute matching result corresponding to the target dataset is determined based on the first recommendation feedback information and the second recommendation feedback information.

[0114] In one example, the first and second recommendation feedback information can be directly used as the attribute matching results.

[0115] In another example, an attribute match can be determined if both the first recommendation feedback information and the second recommendation feedback information are greater than the feedback threshold. Conversely, an attribute match can be determined if either the first recommendation feedback information is not greater than the feedback threshold or the second recommendation feedback information is not greater than the second recommendation feedback information.

[0116] By recommending the multimedia candidate set to the dataset to be recommended, a second recommendation feedback information is obtained, which enables the first recommendation feedback information to be effectively compared, thereby making the attribute matching results more accurate and providing a more effective and accurate reference for multimedia recommendation.

[0117] Figure 6 This is a schematic diagram of a test record according to an exemplary embodiment. Based on this, in one possible implementation, the method may further include: generating an attribute matching report (test report) and report entry information for the attribute matching report based on the attribute matching results; and generating attribute matching record information based on the dataset identifier information (dataset ID), dataset attribute information, and report entry information of the target dataset, wherein the report entry information may be as follows: Figure 6 The operation fields shown correspond to the reports you want to view. For example... Figure 6 As shown, optionally, the attribute matching record information may also include the test status, online status, and the creation time of the test report, which is not limited in this disclosure.

[0118] Optionally, the target dataset can be any one of multiple datasets. The method may further include: in response to a multimedia recommendation request from the terminal, sending attribute matching record information from multiple datasets to the terminal; and upon detecting a request to view target report entry information for target attribute matching record information, sending a target attribute matching report (target test report) corresponding to the target report entry information to the terminal, so that the terminal can display the target attribute matching report, such as... Figure 7As shown. Figure 7 The data source can refer to the source of the test data, such as the client that uploaded the target dataset. The first and second operations can be two of the preset operations, and this disclosure does not limit them. Each dataset has a corresponding attribute matching record, and multiple datasets have multiple attribute matching records. Based on this, the target attribute matching record information can be any one of the multiple attribute matching record information.

[0119] Figure 8 This is a flowchart illustrating the workflow architecture for dataset processing according to an exemplary embodiment. Figure 8 As shown, an upload interface can be provided for uploading the initial dataset and its attribute information. This initial dataset can be stored in a data management platform. The target recommendation platform (multimedia recommendation platform) can filter multiple initial data points in the initial dataset. For example, it can obtain the activity information of multiple initial data points in the target recommendation platform, thereby filtering out initial data points that do not match the activity information to obtain the target dataset. Furthermore, the target recommendation platform can configure a multimedia candidate set for the target dataset, which matches the dataset attribute information of the target dataset. Based on this, the target dataset can be tested, i.e., online recommendation testing can be performed. In the recall phase of online recommendation, the multimedia candidate set is used for targeted recall, combined with other multi-channel recalled multimedia, and recommended to the target dataset to obtain the first recommendation feedback information of the multimedia candidate set. Optionally, the multimedia candidate set and the second associated multimedia set of the dataset to be recommended can be used to recommend the data in the dataset to be recommended, obtaining the second recommendation feedback information of the multimedia candidate set. Therefore, based on the first and second recommendation feedback information, the test result of the target dataset, i.e., the attribute matching result, can be determined. Based on the test results, test reports and test log information can be generated. This allows for the annotation of test results, test reports, and test log information on the target dataset; it also allows for the annotation of the test status on the target dataset, such as "tested". This enables the target dataset to be deployed online, meaning that through the deployment interface, the target dataset, its corresponding test results, test reports, test log information, and test status can be published to a data management platform, such as to the data management server of the target recommendation platform.

[0120] Figure 9 This is a block diagram illustrating a dataset processing apparatus according to an exemplary embodiment. (Refer to...) Figure 9 The device may include:

[0121] The data and multimedia acquisition module 901 is configured to acquire the target dataset to be tested and the multimedia candidate set corresponding to the target dataset. The target dataset includes multiple target datasets, and the multimedia candidate set consists of preset multimedia that matches the dataset attribute information of the target dataset.

[0122] Module 903 is configured to determine the first associated multimedia set of each of the multiple target data sets;

[0123] The first recommendation module 905 is configured to perform recommendation processing on the multimedia candidate set and the first associated multimedia set to multiple target data, and obtain the first recommendation feedback information of the multimedia candidate set.

[0124] The attribute matching result determination module 907 is configured to determine the attribute matching result corresponding to the target dataset based on the first recommendation feedback information.

[0125] In one possible implementation, the first recommendation module 905 mentioned above may include:

[0126] The multimedia set acquisition unit is configured to acquire a multimedia set to be matched that matches the data attribute information of multiple target data.

[0127] The first recommendation unit is configured to perform recommendation processing on multiple target data based on the multimedia candidate set and the first associated multimedia set when the multimedia set to be matched matches the multimedia candidate set, and obtain the first recommendation feedback information of the multimedia candidate set.

[0128] In one possible implementation, the first recommendation module 905 mentioned above may include:

[0129] The sorting unit is configured to perform sorting processing on the candidate multimedia in the multimedia candidate set and the associated multimedia in the first associated multimedia set, and to filter out the multimedia set to be recommended.

[0130] The second recommendation unit is configured to perform recommendation processing on multiple target data based on the multimedia set to be recommended, and to obtain the display information of candidate multimedia and the statistical information of the candidate multimedia being subjected to preset operations.

[0131] The recommendation feedback information acquisition unit is configured to obtain the first recommendation feedback information based on the displayed information and statistical information.

[0132] In one possible implementation, the above-mentioned apparatus may further include:

[0133] The acquisition module is configured to acquire the dataset to be recommended and the second associated multimedia sets of each of the multiple datasets to be recommended in the dataset to be recommended;

[0134] The second recommendation module is configured to perform recommendation processing on multiple data to be recommended based on the multimedia candidate set and the second associated multimedia set, and obtain the second recommendation feedback information of the multimedia candidate set.

[0135] The attribute matching result determination module is also configured to determine the attribute matching result corresponding to the target dataset based on the first recommendation feedback information and the second recommendation feedback information.

[0136] In one possible implementation, the data and multimedia acquisition module 901 described above may include:

[0137] The initial dataset acquisition unit is configured to acquire multiple initial datasets.

[0138] The unit for determining the initial dataset to be tested is configured to perform the task of determining the initial dataset to be tested from multiple initial datasets;

[0139] The activity information acquisition unit is configured to acquire activity information corresponding to multiple initial data in the initial dataset to be tested;

[0140] The target dataset acquisition unit is configured to perform filtering processing on multiple initial data in the initial dataset to be tested based on activity information to obtain the target dataset.

[0141] In one possible implementation, the above-mentioned apparatus may further include:

[0142] The report generation module is configured to generate an attribute matching report and its entry information based on the attribute matching results.

[0143] The test record information generation module is configured to generate attribute matching record information based on the dataset identifier information, dataset attribute information, and report entry information of the target dataset.

[0144] In one possible implementation, the target dataset is any one of a plurality of datasets, and the above-described apparatus may further include:

[0145] The first sending module is configured to execute a multimedia recommendation request in response to the terminal, sending attribute matching record information of multiple datasets to the terminal;

[0146] The second sending module is configured to execute a request to view the target report entry information that detects the target attribute matching record information, and send the target attribute matching report corresponding to the target report entry information to the terminal; the target attribute matching record information is any one of the test record information of multiple datasets.

[0147] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0148] Figure 10 This is a block diagram illustrating an electronic device for data processing according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, this electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for data processing.

[0149] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement a dataset processing method as described in the embodiments of this disclosure.

[0151] In an exemplary embodiment, a computer-readable storage medium is also provided, which, when executed by a processor of an electronic device, enables the electronic device to perform the dataset processing method of the present disclosure embodiments. The computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0152] In an exemplary embodiment, a computer program product including instructions is also provided, which, when run on a computer, causes the computer to perform the data set processing method of the embodiments of this disclosure.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0154] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0155] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method of processing a data set, characterized by, The method comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; the test refers to a test on a matching degree of the target data set and the data set attribute information of the target data set; determining a first associated multimedia set of each of the plurality of target data; based on the multimedia candidate set and the first associated multimedia set, performing recommendation processing on the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; based on the first recommendation feedback information, determining an attribute matching result corresponding to the target data set; the attribute matching result represents a matching test result of the target data set and the data set attribute information of the target data set.

2. The method of claim 1, wherein, The method further comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; the test refers to a test on a matching degree of the target data set and the data set attribute information of the target data set; 3. The method according to claim 1 or 2, characterized in that, determining a first associated multimedia set of each of the plurality of target data; based on the multimedia candidate set and the first associated multimedia set, performing recommendation processing on the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; based on the first recommendation feedback information, determining an attribute matching result corresponding to the target data set; the attribute matching result represents a matching test result of the target data set and the data set attribute information of the target data set.

4. The method of claim 1, wherein, The method further comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; the test refers to a test on a matching degree of the target data set and the data set attribute information of the target data set; determining a first associated multimedia set of each of the plurality of target data; based on the multimedia candidate set and the first associated multimedia set, performing recommendation processing on the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; 5. The method of claim 1, wherein, based on the first recommendation feedback information, determining an attribute matching result corresponding to the target data set; the attribute matching result represents a matching test result of the target data set and the data set attribute information of the target data set. The method further comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; the test refers to a test on a matching degree of the target data set and the data set attribute information of the target data set; 6. The method according to claim 1 or 5, characterized in that, determining a first associated multimedia set of each of the plurality of target data; based on the multimedia candidate set and the first associated multimedia set, performing recommendation processing on the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; based on the first recommendation feedback information, determining an attribute matching result corresponding to the target data set; the attribute matching result represents a matching test result of the target data set and the data set attribute information of the target data set. The method further comprises: obtaining a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching data set attribute information of the target data set; the test refers to a test on a matching degree of the target data set and the data set attribute information of the target data set; determining a first associated multimedia set of each of the plurality of target data; based on the multimedia candidate set and the first associated multimedia set, performing recommendation processing on the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; based on the first recommendation feedback information, determining an attribute matching result corresponding to the target data set; the attribute matching result represents a matching test result of the target data set and the data set attribute information of the target data set. generate an attribute matching report and report entry information of the attribute matching report based on the attribute matching result; generate attribute matching record information according to the data set identification information of the target data set, the data set attribute information and the report entry information.

7. The method of claim 6, wherein, The target data set is any one of a plurality of data sets, and the method further comprises: in response to a multimedia recommendation request of a terminal, sending attribute matching record information of the plurality of data sets to the terminal; detecting a viewing request for target report entry information of target attribute matching record information, and sending a target attribute matching report corresponding to the target report entry information to the terminal; the target attribute matching record information is any one of test record information of the plurality of data sets.

8. A data set processing device, characterized by comprise: a data and multimedia acquisition module configured to acquire a target data set to be tested and a multimedia candidate set corresponding to the target data set, the target data set comprising a plurality of target data, and the multimedia candidate set being a preset multimedia matching the data set attribute information of the target data set; the to-be-tested refers to a test on the matching degree of the target data set and the data set attribute information of the target data set; a determination module configured to determine a first associated multimedia set of each of the plurality of target data; a first recommendation module configured to perform recommendation processing on the multimedia candidate set and the first associated multimedia set to the plurality of target data to obtain first recommendation feedback information of the multimedia candidate set; an attribute matching result determination module configured to determine an attribute matching result corresponding to the target data set based on the first recommendation feedback information; The attribute matching result represents the matching test result of the target data set and the data set attribute information of the target data set.

9. The apparatus of claim 8, wherein, The first recommendation module comprises: a to-be-matched multimedia set acquisition unit configured to acquire a to-be-matched multimedia set matching the data attribute information of each of the plurality of target data; a first recommendation unit configured to perform recommendation processing on the plurality of target data based on the multimedia candidate set and the first associated multimedia set to obtain first recommendation feedback information of the multimedia candidate set in the case that the to-be-matched multimedia set matches the multimedia candidate set.

10. The apparatus of claim 8 or 9, wherein, The first recommendation module comprises: a sorting unit configured to perform sorting processing on candidate multimedia in the multimedia candidate set and associated multimedia in the first associated multimedia set to filter out a to-be-recommended multimedia set; a second recommendation unit configured to perform recommendation processing on the plurality of target data based on the to-be-recommended multimedia set to acquire display information of the candidate multimedia and statistical information of the candidate multimedia being subjected to a preset operation; a recommendation feedback information acquisition unit configured to obtain the first recommendation feedback information based on the display information and the statistical information.

11. The apparatus of claim 8, wherein, The device further comprises: an acquisition module configured to acquire a to-be-recommended data set and a second associated multimedia set of each of a plurality of to-be-recommended data in the to-be-recommended data set; The second recommendation module is configured to perform recommendation processing on the plurality of data to be recommended based on the multimedia candidate set and the second associated multimedia set, to obtain second recommendation feedback information of the multimedia candidate set. The attribute matching result determination module is further configured to determine an attribute matching result corresponding to the target data set based on the first recommendation feedback information and the second recommendation feedback information.

12. The apparatus of claim 8, wherein, The data and multimedia acquisition module comprises: An initial data set acquisition unit configured to perform acquisition of a plurality of initial data sets; A to-be-tested initial data set determination unit configured to perform determination of to-be-tested initial data sets from the plurality of initial data sets; An activity information acquisition unit configured to perform acquisition of activity information corresponding to a plurality of initial data in the to-be-tested initial data sets; A target data set acquisition unit configured to perform filtering processing on the plurality of initial data in the to-be-tested initial data sets based on the activity information, to obtain the target data set.

13. The apparatus of claim 8 or 12, wherein, The apparatus further comprises: A report generation module configured to perform generation of an attribute matching report and report entry information of the attribute matching report based on the attribute matching result; A test record information generation module configured to perform generation of attribute matching record information according to data set identification information, data set attribute information and the report entry information of the target data set.

14. The apparatus of claim 13, wherein, The target data set is any one of a plurality of data sets, and the apparatus further comprises: A first sending module configured to perform sending of attribute matching record information of the plurality of data sets to a terminal in response to a multimedia recommendation request of the terminal; A second sending module configured to perform sending of a target attribute matching report corresponding to target report entry information of target attribute matching record information to the terminal in response to detection of a viewing request of the target report entry information; the target attribute matching record information is any one of test record information of the plurality of data sets.

15. An electronic device, comprising: Comprise: A processor; A memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the data set processing method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, When the instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can perform the data set processing method of any one of claims 1 to 7.

17. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to implement the data set processing method of any one of claims 1 to 7.

Images