CN113327133A - Data recommendation method, data recommendation device, electronic equipment and readable storage medium - Google Patents

Data recommendation method, data recommendation device, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN113327133A
CN113327133A CN202110663421.2A CN202110663421A CN113327133A CN 113327133 A CN113327133 A CN 113327133A CN 202110663421 A CN202110663421 A CN 202110663421A CN 113327133 A CN113327133 A CN 113327133A
Authority
CN
China
Prior art keywords
recommendation
data
feature
dimension data
feature dimension
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110663421.2A
Other languages
Chinese (zh)
Other versions
CN113327133B (en
Inventor
宋云蛟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110663421.2A priority Critical patent/CN113327133B/en
Publication of CN113327133A publication Critical patent/CN113327133A/en
Application granted granted Critical
Publication of CN113327133B publication Critical patent/CN113327133B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The disclosure discloses a data recommendation method, a data recommendation device, an electronic device and a readable storage medium, and relates to the field of big data, in particular to the field of recommendation. The specific implementation scheme is as follows: responding to a request for abnormal recommendation, analyzing the request to obtain feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprises a plurality of feature dimension data; determining one or more alternative feature dimension data corresponding to each of the plurality of feature dimension data; respectively processing each replacement feature data in the plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, wherein the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data; and determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and the second prediction recommendation result.

Description

Data recommendation method, data recommendation device, electronic equipment and readable storage medium
Technical Field
The present disclosure relates to the field of big data technology, and more particularly, to the field of recommendations.
Background
The appearance and popularization of the internet bring a great deal of information to users, and the requirements of the users on the information are met. There may be a problem in that it is difficult for a user to obtain information of interest from a large amount of information when the user is faced with the information.
Therefore, a recommendation system capable of recommending interesting information to the user according to the interest characteristics and behavior habits of the user is developed. For example, a recommendation system for recommending advertisements that will recommend suitable advertisements to a user. However, in the recommendation process, there may be a case where the recommendation result is not as expected.
Disclosure of Invention
The disclosure provides a data recommendation method, a data recommendation device, an electronic device and a readable storage medium.
According to an aspect of the present disclosure, there is provided a data recommendation method including: responding to a request for abnormal recommendation, analyzing the request to obtain feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprise a plurality of feature dimension data; determining one or more alternative feature dimension data corresponding to each of the plurality of feature dimension data; processing each replacement feature data in a plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, wherein the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data; and determining target feature dimension data which is considered to cause the abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and the second prediction recommendation result.
According to another aspect of the present disclosure, there is provided a feature recommendation device including: the analysis module is used for responding to a request for abnormal recommendation, analyzing the request and obtaining feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprise a plurality of feature dimension data; a first determining module, configured to determine one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data; an obtaining module, configured to respectively process each of a plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each of the replacement feature data, where the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data; and a second determining module, configured to determine, according to the first prediction recommendation result and the second prediction recommendation result, target feature dimension data that is considered to cause the abnormal recommendation from the plurality of feature dimension data.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method as described above.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method as described above.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 schematically illustrates an exemplary system architecture to which the data recommendation method and apparatus may be applied, according to an embodiment of the present disclosure;
FIG. 2 schematically shows a flow chart of a data recommendation method according to an embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow diagram for determining one or more alternative feature dimension data corresponding to each of a plurality of feature dimension data, in accordance with an embodiment of the present disclosure;
FIG. 4 schematically illustrates a flow diagram for determining target feature dimension data from a plurality of feature dimension data that is believed to result in an anomalous recommendation based on a first predicted recommendation and a second predicted recommendation, in accordance with an embodiment of the present disclosure;
FIG. 5 schematically illustrates a schematic diagram of a data recommendation process according to an embodiment of the disclosure;
FIG. 6 schematically shows a block diagram of a data recommendation device according to an embodiment of the present disclosure; and
fig. 7 shows a block diagram of an electronic device that may be suitable for use in a data recommendation method according to an embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the recommendation system, recommendation can be realized by using a recommendation model obtained by training the deep neural network model by using the training samples. Because the deep neural network model has stronger generalization capability, the recommendation model can be realized in a mode of continuously updating the training samples to update the model under the condition of determining the model parameters, and the recommendation model has better prediction effect.
In the process of implementing the disclosed concept, it is found that there are situations where the recommendation result is not as expected, which will affect the user experience and may cause waste of resources. In order to effectively guarantee the use experience of the user and reduce the waste of resources, the method can be realized by improving the prediction accuracy of the recommendation model. In order to improve the prediction accuracy of the recommendation model, reasons causing non-compliance with the expected recommendation result may be analyzed to improve the recommendation model based on the analyzed reasons.
The reason for causing the unexpected recommendation result can be analyzed by respectively and randomly replacing the value of each plaintext field, processing the replaced plaintext field by using an offline recommendation model to obtain a predicted recommendation result corresponding to the replaced plaintext field, comparing the predicted recommendation result corresponding to the replaced plaintext field with the predicted recommendation result corresponding to the original plaintext field, and determining the target plaintext field which is considered to cause the unexpected recommendation result according to the comparison result. Each plaintext field may understand user data related to a recommendation that can be intuitively understood.
In the process of implementing the present disclosure, it is found that because the usage manner of the feature dimension data of the recommendation model is complex, for example, one feature dimension data corresponds to a plurality of plaintext fields or a plurality of feature dimension data corresponds to a plaintext field, it is difficult to implement a manner of replacing plaintext fields to determine the reason that the recommendation result is not in accordance with the expectation with high accuracy. In addition, since the online recommendation model is actually used by the recommendation system instead of the offline recommendation model, the offline recommendation model and the online recommendation model are inconsistent, for example, some parameters that may have a large influence on the offline recommendation model may not have a large influence on the online recommendation model. Therefore, it is difficult to more accurately determine the reason for the non-compliance with the expected recommendation results using the offline recommendation model.
For this reason, a scheme is proposed which enables determination of the cause of disagreement with the expected recommendation result from the predicted recommendation result obtained by processing the data of the feature level with an online recommendation model. That is, the disclosed embodiments provide a data recommendation method, a data recommendation apparatus, an electronic device, a non-transitory computer-readable storage medium storing computer instructions, and a computer program product. The data recommendation method comprises the following steps: the method comprises the steps of responding to a request for abnormal recommendation, analyzing the request to obtain feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprise a plurality of feature dimension data, determining one or more replacement feature dimension data corresponding to each feature dimension data in the feature dimension data, processing each replacement feature data in the replacement feature data by using an online recommendation model respectively to obtain a second prediction recommendation result corresponding to each replacement feature data, wherein the replacement feature data are obtained based on the feature data and the replacement feature dimension data, and determining target feature dimension data which are considered to cause abnormal recommendation from the feature dimension data according to the first prediction recommendation result and the second prediction recommendation result.
Fig. 1 schematically illustrates an exemplary system architecture 100 to which the data recommendation method and apparatus may be applied, according to an embodiment of the present disclosure.
It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture 100 to which the data recommendation method and apparatus may be applied may include a terminal device, but the terminal device may implement the data recommendation method and apparatus provided in the embodiments of the present disclosure without interacting with a server.
As shown in fig. 1, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as a knowledge reading application, a web browser application, a search application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (for example only) providing support for content browsed by the user using the terminal devices 101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that the data recommendation method provided by the embodiment of the present disclosure may be generally executed by the terminal device 101, 102, or 103. Accordingly, the data recommendation device provided by the embodiment of the present disclosure may also be disposed in the terminal device 101, 102, or 103.
Alternatively, the data recommendation method provided by the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the data recommendation device provided by the embodiment of the present disclosure may be generally disposed in the server 105. The data recommendation method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the data recommendation device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
For example, in response to a request for abnormal recommendation, server 105 parses the request to obtain feature data and a first predicted recommendation corresponding to the feature data, determines one or more replacement feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data, processes each replacement feature data in the plurality of replacement feature data using an online recommendation model to obtain a second predicted recommendation corresponding to each replacement feature data, and determines target feature dimension data from the plurality of feature dimension data that is considered to cause abnormal recommendation according to the first predicted recommendation and the second predicted recommendation. Or by a server or server cluster capable of communicating with the terminal devices 101, 102, 103 and/or the server 105, and ultimately enables the determination of the target feature dimension data that is believed to lead to the anomalous recommendations.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
FIG. 2 schematically shows a flow diagram of a data recommendation method 200 according to an embodiment of the disclosure.
As shown in fig. 2, the method includes operations S210 to S240.
In operation S210, in response to a request for abnormal recommendation, the request is parsed to obtain feature data and a first prediction recommendation result corresponding to the feature data, where the feature data includes a plurality of feature dimension data.
In operation S220, one or more replacement feature dimension data corresponding to each feature dimension data of the plurality of feature dimension data is determined.
In operation S230, each of a plurality of replacement feature data is processed by using an online recommendation model, and a second predicted recommendation result corresponding to each replacement feature data is obtained, wherein the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data.
In operation S240, target feature dimension data that is considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the first prediction recommendation and the second prediction recommendation.
According to an embodiment of the present disclosure, an abnormal recommendation may refer to a recommendation whose recommendation result does not conform to the expectation, i.e., a recommendation whose recommendation result and the expectation recommendation result do not conform. The feature data may be data obtained by extracting features of user data related to the recommendation. The feature data may include at least two feature dimension data, i.e., the dimensions of the feature data may include at least two, and the feature data of each dimension may be referred to as feature dimension data. Each feature dimension data may have one or more alternative feature dimension data corresponding to the feature dimension data. The feature dimension data and the replacement feature dimension data corresponding to the feature dimension data are different in value, that is, the feature dimension data and the replacement feature dimension data corresponding to the feature dimension data represent the same feature dimension, and the difference is a value.
According to the embodiment of the disclosure, for each feature dimension data, the replacement feature data corresponding to the feature dimension data can be obtained according to the feature data corresponding to the feature dimension data and the replacement feature dimension data.
According to an embodiment of the present disclosure, the first prediction recommendation result corresponding to the feature data may be obtained by processing the feature data using an online recommendation model, that is, the first prediction recommendation result is a prediction recommendation result obtained using the online recommendation model.
According to the embodiment of the disclosure, the reason why the online recommendation model is used for processing the feature data to obtain the first prediction recommendation result is that: in the recommendation system, a user who invests cost is more interested in the conversion effect, but the conversion data is less, and the generalization capability of the online recommendation model is not enough to bear the conversion effect completely, so in order to solve the problem, the prediction recommendation result obtained by using the online recommendation model can be calibrated by using a feedback coefficient, and therefore the prediction recommendation result can be obtained by calibrating the original prediction recommendation result by using the feedback coefficient. The feedback coefficient may be understood as being determined from a posteriori data relating to the conversion effect.
However, the reason for determining the recommendation result that is not in line with the expected recommendation result needs to be analyzed, and if the prediction recommendation result is not the prediction recommendation result obtained by using the online recommendation model but the prediction recommendation result obtained by calibrating the prediction recommendation result obtained by using the online recommendation model, the reason for determining the recommendation result that is not in line with the expected recommendation result may be inconsistent with the actual situation due to the addition of other factors. Therefore, in order to ensure that the determined reason causing the non-conforming recommendation result is accurate as much as possible, the first prediction recommendation result corresponding to the feature data may be a prediction recommendation result obtained by processing the feature data by using the online recommendation model instead of calibrating the first prediction recommendation result obtained by using the online recommendation model.
According to an embodiment of the present disclosure, an online recommendation model may be understood as a recommendation model that is actually utilized by a recommendation system. The online recommendation model may be used to make object recommendations to users. The online recommendation model can be obtained by training the deep neural network model by using the training samples.
According to an embodiment of the disclosure, in the case that an abnormal recommendation is detected, a request for the abnormal recommendation may be generated, and the request may include feature data and a first predicted recommendation corresponding to the feature data. Generating a request for exception recommendations may include: and acquiring data related to the abnormal recommendation from the target file, loading the data related to the abnormal recommendation to a memory, and processing the data related to the abnormal recommendation to obtain a request for the abnormal recommendation in a target format, wherein the target format can comprise a Proto Buffer. In the case where a request for abnormal recommendation is acquired, the request may be parsed in response to the request to obtain feature data and a first predicted recommendation corresponding to the feature data. The above-mentioned request for obtaining the abnormal recommendation may be understood as being implemented by an online request module. The module for generating and sending a request for exception recommendations may send the request for exception recommendations to the online request module through a remote procedure call.
According to embodiments of the present disclosure, since it is difficult for the online request module to implement the request for receiving the feature level, the online request module may be improved so that it can support the request for receiving the feature level. In an embodiment of the disclosure, the online request module for performing receiving a request for an exception recommendation is an online request module capable of receiving a request for a feature level.
According to the embodiment of the disclosure, in order to ensure that the determined reason causing the inconsistent recommendation result is accurate as much as possible, the consistency between the online request module and the online recommendation model needs to be ensured as much as possible, and in order to ensure the consistency between the online request module and the online recommendation model as much as possible, the codes of the online request module and the online recommendation model can be subjected to homologous management.
In addition, the switch module may be used to control whether the online request module capable of receiving the feature level request is activated, that is, if the switch state of the switch module is in the on state, it may be stated that the online request module capable of receiving the feature level request is activated. If the switch state of the switch model is in the off state, it may be stated that the on-line request module that has turned off the request capable of receiving the feature level may include the switch modules in the on state and the off state to use the switch control model module to receive the request for the feature level.
According to the embodiment of the disclosure, after the request is parsed to obtain the feature data, one or more replacement dimension feature data corresponding to each feature dimension data included in the feature data may be determined, and each replacement feature data may be determined according to the feature data and each replacement feature dimension data corresponding to each feature dimension data, that is, each replacement feature data in the plurality of replacement feature data is obtained based on the feature data and each replacement feature dimension data corresponding to each feature dimension data. That is, for each feature dimension data corresponding to the feature data, for each replacement feature dimension data corresponding to the feature dimension data, the replacement feature dimension data is used to replace the feature dimension data in the feature data, and the feature dimension data is combined with other feature dimension data except the feature dimension data in the feature data to serve as a replacement feature data corresponding to the feature data.
According to an embodiment of the present disclosure, in accordance with determining one or more alternative feature dimension data corresponding to each of a plurality of feature dimension data, may include: one or more replacement feature dimension data corresponding to each feature dimension data of the plurality of feature dimension data is determined using a random replacement method.
Alternatively, a training sample corresponding to the historical online recommendation model is determined, and the training sample corresponding to the historical online recommendation model is processed to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
Alternatively, a training sample corresponding to the online recommendation model is determined, and the training sample corresponding to the online recommendation model is processed to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
According to the embodiment of the disclosure, the online recommendation model described above can be understood as an online recommendation model for generating abnormal recommendations. The online recommendation model can be updated according to actual business requirements, so that online recommendation models of multiple versions can be generated, and online recommendation models which are used historically can be called historical online recommendation models.
According to an embodiment of the present disclosure, determining one or more replacement feature dimension data corresponding to each feature dimension data of a plurality of feature dimension data by using a random replacement method may include: and aiming at each characteristic dimension data in the characteristic dimension data, determining each value corresponding to the characteristic dimension data, and randomly selecting one or more values from a value set as a replacement characteristic dimension data corresponding to the characteristic dimension data.
According to an embodiment of the present disclosure, processing a training sample corresponding to a historical online recommendation model to obtain one or more alternative feature dimension data corresponding to each feature dimension data in a plurality of feature dimension data may include: and processing the training samples corresponding to the historical online recommendation model to obtain values of each feature dimension data appearing in the historical training samples, and processing each value to obtain each replacement feature dimension data corresponding to each feature dimension data. Processing each value to obtain each alternative feature dimension data corresponding to each feature dimension data, which may include: and combining the values to obtain one or more combined values, and taking each combined value as each alternative feature dimension data corresponding to each feature dimension data. Alternatively, each value is taken as each alternative feature dimension data corresponding to each feature dimension data. The historical training samples can be understood as training samples corresponding to the historical online recommendation model.
According to the embodiment of the disclosure, after obtaining each replacement feature data corresponding to the feature data, each replacement feature data may be processed by using the online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, that is, each replacement feature data may be input into the online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data. Because the replacement characteristic data is processed by using the online recommendation model which is actually used by the recommendation system, the accuracy of the prediction recommendation result can be effectively ensured.
According to the embodiment of the disclosure, after the first prediction recommendation result corresponding to the feature data and the second prediction recommendation result corresponding to each replacement feature data are obtained, the first prediction recommendation result may be respectively compared with each of the plurality of second prediction recommendation results to obtain a comparison result, and the target feature dimension data may be determined from the plurality of feature dimension data according to the comparison result. The target feature dimension data may be understood as feature dimension data that is considered to result in anomalous recommendations. The target feature dimension data may include one or more.
According to an embodiment of the present disclosure, comparing the first predicted recommendation with each of the plurality of second predicted recommendations, the obtaining the comparison result may include: and determining a prediction recommendation result corresponding to each alternative feature data set according to the second prediction recommendation result corresponding to each alternative feature data included in each alternative feature dimension data set. And comparing the first prediction recommendation result with the prediction recommendation result corresponding to each replacement characteristic data set to obtain a comparison result.
According to an embodiment of the present disclosure, determining a predicted recommendation corresponding to each alternative feature data set according to the second predicted recommendation corresponding to each alternative feature data included in each alternative feature dimension data set may include: and determining a maximum value, wherein the maximum value is the maximum value of the prediction recommendation result corresponding to each replacement feature data included in each replacement feature data set, and the maximum value or the minimum value is included in the maximum value or the minimum value. The most value is determined as the predicted recommendation corresponding to each alternative feature data set. Alternatively, an average value is determined, wherein the average value is an average value of the predicted recommendation corresponding to the respective replacement feature data included in each replacement feature data set. The average is determined as the predicted recommendation corresponding to each alternative feature data set.
According to the embodiment of the disclosure, the target feature dimension data causing abnormal recommendation is determined, so that the target feature dimension data can be regarded as data needing recommendation, the direction which can be optimized by an online recommendation model can be determined according to the target feature dimension data, and the probability that the recommendation result is not in line with expectation is effectively reduced.
It should be noted that, in the technical solution of the embodiment of the present disclosure, the acquisition, storage, application, and the like of the related feature data and the replacement feature dimension data all conform to the regulations of the related laws and regulations, and necessary security measures are taken without violating the good customs of the public order.
According to the embodiment of the disclosure, the request is analyzed in response to the request for abnormal recommendation to obtain feature data and a first prediction recommendation result corresponding to the feature data, one or more replacement feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data are determined, each replacement feature data in the plurality of replacement feature data is processed by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, and target feature dimension data considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the first prediction recommendation result and the second prediction recommendation result. Since the replacement feature data is obtained based on the feature data and each replacement feature dimension data corresponding to each feature dimension data, the recognition of the feature level is realized. On the basis, the online recommendation model is utilized to process the replacement feature data to obtain the second prediction recommendation result corresponding to the replacement feature data, and the online recommendation model is actually utilized by the recommendation system, so that the accuracy of the prediction recommendation result can be effectively ensured, and further the technical problem that the reason of the inconsistent recommendation result is determined by the online recommendation model is at least partially overcome because the target feature dimension data which is considered to cause abnormal recommendation is determined to be accurate from the plurality of feature dimension data according to the first prediction recommendation result and each second prediction recommendation result corresponding to the feature data, so that the direction which can be optimized by the online recommendation model can be determined according to the target feature dimension data, and the probability that the recommendation result is inconsistent is reduced.
According to an embodiment of the present disclosure, the data recommendation method may further include the following operations.
Under the condition that the first prediction recommendation result is detected to meet a preset condition, generating a request for abnormal recommendation, wherein the preset condition comprises one of the following conditions: the first predicted recommendation is greater than or equal to a first threshold. The first predicted recommendation is less than or equal to a second threshold, wherein the second threshold is less than or equal to the first threshold. A first difference between the first predicted recommendation and the historical recommendation is greater than or equal to a first difference threshold.
According to an embodiment of the present disclosure, a preset condition may be used as a basis for determining whether a recommendation is an abnormal recommendation. The values of the first threshold, the second threshold and the first difference threshold may be configured according to actual service requirements, and are not limited herein.
According to the embodiment of the disclosure, after the first prediction recommendation result corresponding to the feature data is obtained, whether the first prediction recommendation result meets the prediction condition or not may be determined, and if the first prediction recommendation result is determined to meet the preset condition, the recommendation generating the first prediction recommendation result may be an abnormal recommendation. If the first prediction recommendation result is determined not to meet the preset condition, the recommendation generating the first prediction recommendation result can be indicated to be a non-abnormal recommendation. If it is determined that the recommendation that produced the first predicted recommendation is an anomalous recommendation, a request for an anomalous recommendation may be generated.
According to the embodiment of the disclosure, in the case that it is detected that the first predicted recommendation result satisfies the preset condition, generating the request for the abnormal recommendation may include the following operations.
And under the condition that the first prediction recommendation result is detected to meet the preset condition, generating a request for abnormal recommendation within a preset time period.
According to the embodiment of the present disclosure, in the case of an online recommendation system, there is a high demand for efficiency in determining the cause of the non-compliant recommendation result. In order to improve the efficiency of determining the reason causing the unexpected recommendation result, the request for the abnormal recommendation can be generated in time when the first predicted recommendation result is detected to meet the preset condition, so that the reason causing the abnormal recommendation can be analyzed in time. For example, a request for an exception recommendation may be generated within a preset time period. The value of the preset time period may be configured according to the actual service requirement, and is not limited herein.
According to the embodiment of the disclosure, the request for the abnormal recommendation is generated in the preset time period under the condition that the first prediction recommendation result is detected to meet the preset condition, so that the reason causing the abnormal recommendation can be analyzed in time, the recommendation meeting the expectation can be provided for the user, and the use experience of the user is improved.
According to an embodiment of the disclosure, in response to a request for abnormal recommendation, parsing the request to obtain feature data and a first predicted recommendation corresponding to the feature data may include the following operations.
And analyzing the request within the expected analysis time period of the received request to obtain the characteristic data and a first prediction recommendation result corresponding to the characteristic data.
According to the embodiment of the disclosure, in order to improve the efficiency of determining the reason causing the unexpected recommendation result, the analysis of the request can be completed within the expected analysis time period in which the request is received, so that the reason causing the abnormal recommendation can be analyzed in a timely manner.
According to the embodiment of the disclosure, the processing of each of the plurality of replacement feature data by the online recommendation model to obtain the second predicted recommendation result is realized by multithreading.
According to embodiments of the present disclosure, to improve the efficiency of determining the cause of the non-compliance with the expected recommended result, a multi-threaded implementation may be utilized, i.e., multiple alternative feature data may be processed by at least two threads. Further, different threads may be deployed on the same electronic device or on different electronic devices.
According to an embodiment of the present disclosure, the request further comprises an online model version identification.
Operation S230 may include the following operations.
And respectively processing the plurality of replacement characteristic data by using the online recommendation model corresponding to the online model version identification to obtain a second prediction recommendation result corresponding to each replacement characteristic data.
According to the embodiment of the disclosure, since the online recommendation model can be updated according to actual business requirements, there may be multiple versions of the online recommendation model, and thus there may be a case where the online recommendation model currently being utilized is inconsistent with the online recommendation model that causes the recommendation result to be not as expected. In order to ensure that the determined reason causing the unexpected recommendation result is accurate as much as possible, each of the plurality of alternative feature data needs to be processed by using the online recommendation model causing the unexpected recommendation result.
In order to enable each of the plurality of alternative feature data to be processed using an online recommendation model that results in a recommendation that is not as expected, each version of the online recommendation model may be stored for subsequent use. The online recommendation model may be characterized with an online model version identification. On this basis, generating a request for exception recommendations may also include an online model version identification. The online model version identification included in the request may be an online model version identification of the online recommendation model that generated the exception recommendation.
According to the embodiment of the disclosure, an online recommendation model corresponding to the online model version identifier may be determined according to the online model version identifier, that is, an online recommendation model generating abnormal recommendation is determined, and each replacement feature data in the plurality of replacement feature data is processed by using the online recommendation model generating abnormal recommendation, so as to obtain a second prediction recommendation result corresponding to each replacement feature data.
The method shown in fig. 2 is further described with reference to fig. 3-5 in conjunction with specific embodiments.
Fig. 3 schematically illustrates a flow diagram for determining one or more alternative feature dimension data 300 corresponding to each feature dimension data of a plurality of feature dimension data according to an embodiment of the present disclosure.
As shown in fig. 3, the method includes operations S321 to S322.
In operation S321, training samples corresponding to the online recommendation model are determined.
In operation S322, the training samples corresponding to the online recommendation model are processed to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
According to the embodiment of the disclosure, the training sample corresponding to the online recommendation model may be understood as a training sample for training an online recommendation model generating abnormal recommendations.
According to the embodiment of the disclosure, the training samples corresponding to the online recommendation model are processed to obtain the value of each feature dimension data appearing in the training samples, and each value is processed to obtain each replacement feature dimension data corresponding to each feature dimension data. Processing each value to obtain each alternative feature dimension data corresponding to each feature dimension data, which may include: and combining the values to obtain one or more combined values, and taking each combined value as each alternative feature dimension data corresponding to each feature dimension data. Alternatively, each value is taken as each alternative feature dimension data corresponding to each feature dimension data.
According to the embodiment of the disclosure, as the training samples for training the online recommendation model are utilized to obtain one or more pieces of replacement feature dimension data corresponding to each piece of feature dimension data, the obtained replacement feature dimension data is meaningful, complete and time-efficient, and therefore, higher-quality data support can be provided for ensuring the determined reason which causes the failure to meet the expected recommendation result as much as possible.
According to the embodiment of the present disclosure, in order to improve the efficiency of determining the cause of the non-compliance with the expected recommendation result, the replacement feature dimension data may be generated in advance and stored in the cache.
Fig. 4 schematically illustrates a flow diagram of determining target feature dimension data 400 from a plurality of feature dimension data that is believed to result in an anomalous recommendation based on a first predicted recommendation and a second predicted recommendation, according to an embodiment of the disclosure.
As shown in fig. 4, the method includes operations S441 to S442.
In operation S441, a third predicted recommendation corresponding to each alternative feature data set is determined according to a second predicted recommendation corresponding to each alternative feature data included in each alternative feature dimension data set, where each feature dimension data set corresponds to one alternative feature dimension data set.
In operation S442, target feature dimension data that is considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the first predicted recommendation and each of the third predicted recommendations.
According to an embodiment of the present disclosure, for each feature dimension data, one replacement feature dimension data set corresponding to the feature dimension data may be determined, and each replacement feature dimension data set may include one or more replacement feature dimension data.
According to the embodiment of the disclosure, the first prediction result may be compared with each third prediction result respectively to obtain a comparison result, and according to the comparison result, target feature dimension data considered to cause abnormal recommendation is determined from the plurality of feature dimension data.
Operation S441 may include the following operations according to an embodiment of the present disclosure.
An average value is determined, wherein the average value is an average value of the predicted recommendation results corresponding to the respective replacement feature data included in each replacement feature data set. The average is determined as the third predicted recommendation corresponding to each replacement feature data set.
According to the embodiment of the disclosure, for each replacement feature data set, the prediction recommendation results corresponding to the replacement feature set are added to obtain a sum, and a ratio of the sum to the number of the replacement feature data included in the replacement feature data set is determined, wherein the ratio is an average value. The average is determined as a third predicted recommendation corresponding to the replacement feature data set.
According to an embodiment of the present disclosure, determining, from the plurality of feature dimension data, target feature dimension data that is considered to cause abnormal recommendation according to the first prediction recommendation and each of the third prediction recommendations may include the following operations.
A second difference between the first predicted recommendation and each third predicted recommendation is determined. And determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the plurality of second difference values.
According to an embodiment of the disclosure, a second difference between the first predicted recommendation and each third predicted recommendation may be determined, resulting in a plurality of second differences. Determining target feature dimension data from the plurality of feature dimension data that is considered to result in the abnormal recommendation based on the second plurality of differences may include: target feature dimension data that is considered to result in an anomaly recommendation may be determined from the plurality of feature dimension data based on the second difference threshold and the plurality of second differences. Alternatively, the plurality of second difference values are sorted to obtain a sorting result, and target feature dimension data which is considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the sorting result.
According to an embodiment of the present disclosure, determining, from the plurality of feature dimension data, target feature dimension data that is considered to cause the abnormal recommendation according to the plurality of second difference values may include the following operations.
And for each piece of feature dimension data, determining the feature dimension data as target feature dimension data considered to cause abnormal recommendation if it is determined that the second difference corresponding to the feature dimension data is greater than or equal to the second difference threshold.
According to an embodiment of the present disclosure, the second difference threshold may be used as one of the bases for determining the target feature dimension data from the plurality of feature dimension data. The value of the second difference threshold may be configured according to the actual service requirement, and is not limited herein.
According to an embodiment of the present disclosure, determining, from the plurality of feature dimension data, target feature dimension data that is considered to cause the abnormal recommendation according to the plurality of second difference values may include the following operations.
And sequencing the plurality of second difference values to obtain a sequencing result. And determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the sorting result.
According to the embodiment of the disclosure, the plurality of second difference values are sorted to obtain a sorting result, and target feature dimension data which is considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the sorting result. The sorting may include sorting in an order of the second difference values from small to large or sorting in an order of the second difference values from large to small.
Fig. 5 schematically shows a schematic diagram of a data recommendation process 500 according to an embodiment of the present disclosure.
As shown in fig. 5, in the case where it is detected that the first predicted recommendation 503 satisfies the preset condition, a request 501 for an abnormal recommendation is generated. In response to the request 501 for the abnormal recommendation, the request 501 for the abnormal recommendation is analyzed to obtain feature data 502 and a first prediction recommendation result 503 corresponding to the feature data 502. The feature data 503 may include a plurality of feature dimension data.
One or more alternative feature dimension data corresponding to each feature dimension data is determined. And determining each alternative feature data according to the feature data and each alternative feature dimension data corresponding to each feature dimension data. A replacement feature data set 504 corresponding to each feature dimension data is derived from one or more replacement feature data corresponding to each feature dimension data.
Each replacement feature data included in each replacement feature data set 504 is processed by using an online recommendation model, and a second prediction recommendation result 505 corresponding to each replacement feature data is obtained.
The first prediction recommendation result 503 and each second prediction recommendation result 505 are compared to obtain a comparison result, and target feature dimension data 507 which is considered to cause abnormal recommendation is determined from the plurality of feature dimension data according to the comparison result.
Fig. 6 schematically shows a block diagram of a data recommendation device 600 according to an embodiment of the present disclosure.
As shown in fig. 6, the data recommendation apparatus 600 may include a parsing module 610, a first determining module 620, an obtaining module 630, and a second determining module 640.
The analysis module 610 is configured to, in response to a request for abnormal recommendation, analyze the request to obtain feature data and a first prediction recommendation result corresponding to the feature data, where the feature data includes a plurality of feature dimension data.
A first determination module 620 is configured to determine one or more alternative feature dimension data corresponding to each feature dimension data of the plurality of feature dimension data.
An obtaining module 630, configured to process each of the multiple replacement feature data by using the online recommendation model, respectively, to obtain a second predicted recommendation result corresponding to each of the replacement feature data, where the multiple replacement feature data are obtained based on the feature data and the multiple replacement feature dimension data.
And a second determining module 640, configured to determine, according to the first prediction recommendation result and the second prediction recommendation result, target feature dimension data that is considered to cause abnormal recommendation from the plurality of feature dimension data.
According to an embodiment of the present disclosure, the first determination module 620 may include a first determination submodule and a second processing submodule.
And the first determining submodule is used for determining the training sample corresponding to the online recommendation model.
The first processing submodule is used for processing the training sample corresponding to the online recommendation model to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
According to an embodiment of the present disclosure, the data recommendation apparatus 600 may further include a generation module.
The generation module is used for generating a request for abnormal recommendation when the first prediction recommendation result is detected to meet a preset condition, wherein the preset condition comprises one of the following conditions: the predicted recommendation is greater than or equal to a first threshold. The first predicted recommendation is less than or equal to a second threshold, wherein the second threshold is less than or equal to the first threshold. A first difference between the first predicted recommendation and the historical recommendation is greater than or equal to a first difference threshold.
According to an embodiment of the present disclosure, the generating module may include a generating submodule.
And the generation submodule is used for generating a request for abnormal recommendation within a preset time period under the condition that the first prediction recommendation result is detected to meet a preset condition.
According to an embodiment of the present disclosure, the request further comprises an online model version identification.
The obtaining module 630 may include an obtaining sub-module.
And the obtaining submodule is used for respectively processing a plurality of replacement characteristic data by using the online recommendation model corresponding to the online model version identification to obtain a second prediction recommendation result corresponding to each replacement characteristic data.
According to the embodiment of the disclosure, each of the plurality of replacement feature data is processed by using the online recommendation model, and the second prediction recommendation result corresponding to each replacement feature data is obtained by multithreading.
According to an embodiment of the present disclosure, the second determination module 640 may include a second determination submodule and a third determination submodule.
And the second determining submodule is used for determining a third prediction recommendation result corresponding to each alternative feature data set according to a second prediction recommendation result corresponding to each alternative feature data included in each alternative feature dimension data set, wherein each feature dimension data corresponds to one alternative feature dimension data set.
And the third determining submodule is used for determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and each third prediction recommendation result.
According to an embodiment of the present disclosure, the second determination submodule may include a first determination unit and a second determination unit.
And a first determining unit, configured to determine an average value, where the average value is an average value of the predicted recommendation results corresponding to the respective replacement feature data included in each replacement feature data set.
A second determination unit configured to determine the average as a third prediction recommendation corresponding to each of the alternative feature data sets.
According to an embodiment of the present disclosure, the third determination submodule may include a third determination unit and a fourth determination unit.
A third determination unit to determine a second difference between the first predicted recommendation and each third predicted recommendation.
And a fourth determining unit configured to determine, from the plurality of feature dimension data, target feature dimension data that is considered to cause the abnormal recommendation, according to the plurality of second difference values.
According to an embodiment of the present disclosure, the fourth determination unit may include a first determination subunit.
And the first determining subunit is used for determining the characteristic dimension data as the target characteristic dimension data which is considered to cause abnormal recommendation under the condition that the second difference corresponding to the characteristic dimension data is determined to be greater than or equal to the second difference threshold value aiming at each characteristic dimension data.
According to an embodiment of the present disclosure, the fourth determination unit may include a sorting subunit and a second determination subunit.
And the sorting subunit is used for sorting the plurality of second difference values to obtain a sorting result.
And the second determining subunit is used for determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the sorting result.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.
According to an embodiment of the present disclosure, a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described above.
According to an embodiment of the disclosure, a computer program product comprising a computer program which, when executed by a processor, implements the method as described above.
Fig. 7 shows a block diagram of an electronic device 700 that may be suitable for use in a data recommendation method according to an embodiment of the disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM702, and the RAM703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 executes the respective methods and processes described above, such as the data recommendation method. For example, in some embodiments, the data recommendation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM702 and/or communications unit 709. When the computer program is loaded into the RAM703 and executed by the computing unit 701, one or more steps of the data recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the XXX method by any other suitable means (e.g., by way of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (20)

1. A method of data recommendation, comprising:
responding to a request for abnormal recommendation, analyzing the request to obtain feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprises a plurality of feature dimension data;
determining one or more replacement feature dimension data corresponding to each feature dimension data of the plurality of feature dimension data;
respectively processing each replacement feature data in a plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, wherein the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data; and
and determining target feature dimension data which is considered to cause the abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and the second prediction recommendation result.
2. The method of claim 1, wherein the determining one or more alternative feature dimension data corresponding to each of the plurality of feature dimension data comprises:
determining a training sample corresponding to the online recommendation model; and
and processing the training samples corresponding to the online recommendation model to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
3. The method of claim 1 or 2, further comprising:
generating the request for abnormal recommendation in case of detecting that the first predicted recommendation satisfies a preset condition,
wherein the preset condition comprises one of:
the first predicted recommendation is greater than or equal to a first threshold;
the first predicted recommendation is less than or equal to a second threshold, wherein the second threshold is less than or equal to the first threshold;
a first difference between the first predicted recommendation and the historical recommendation is greater than or equal to a first difference threshold.
4. The method of claim 3, wherein the generating the request for abnormal recommendation in the case of detecting that the first predicted recommendation satisfies a preset condition comprises:
and generating the request for abnormal recommendation within a preset time period under the condition that the first prediction recommendation result is detected to meet a preset condition.
5. The method of any of claims 1-4, wherein the request further includes an online model version identification;
the method for processing each replacement feature data in a plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data comprises the following steps:
and respectively processing the plurality of replacement characteristic data by using the online recommendation model corresponding to the online model version identification to obtain a second prediction recommendation result corresponding to each replacement characteristic data.
6. The method according to any one of claims 1 to 4, wherein the processing each of the plurality of replacement feature data by using the online recommendation model to obtain the second predicted recommendation corresponding to each replacement feature data is realized by multithreading.
7. The method of any of claims 2-6, wherein the determining, from the plurality of feature dimension data, a target feature dimension data that is believed to result in the anomalous recommendation based on the first and second predicted recommendations comprises:
determining a third prediction recommendation result corresponding to each replacement feature data set according to a second prediction recommendation result corresponding to each replacement feature data included in each replacement feature dimension data set, wherein each feature dimension data corresponds to one replacement feature dimension data set; and
and determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and each third prediction recommendation result.
8. The method of claim 7, wherein the determining a third predicted recommendation corresponding to each of the alternative feature data sets from the second predicted recommendation corresponding to each of the alternative feature data included in each of the alternative feature dimension data sets comprises:
determining an average value, wherein the average value is an average value of predicted recommendation results corresponding to the replacement feature data included in each replacement feature data set; and
determining the average as a third predicted recommendation corresponding to each of the alternative feature data sets.
9. The method of claim 7 or 8, wherein the determining, from the plurality of feature dimension data, a target feature dimension data that is believed to result in the anomalous recommendation in accordance with the first predictive recommendation and each of the third predictive recommendations comprises:
determining a second difference between the first predicted recommendation and each of the third predicted recommendations; and
and determining target feature dimension data which is considered to cause the abnormal recommendation from the plurality of feature dimension data according to a plurality of second difference values.
10. The method of claim 9, wherein said determining, from the plurality of feature dimension data, a target feature dimension data that is believed to result in the anomalous recommendation based on the plurality of second difference values comprises:
for each of the feature dimension data, in a case where it is determined that a second difference corresponding to the feature dimension data is greater than or equal to a second difference threshold, determining the feature dimension data as target feature dimension data that is considered to cause the abnormal recommendation.
11. The method of claim 9, wherein said determining, from the plurality of feature dimension data, a target feature dimension data that is believed to result in the anomalous recommendation based on the plurality of second difference values comprises:
sequencing the plurality of second difference values to obtain a sequencing result; and
according to the sorting result, target feature dimension data which is considered to cause the abnormal recommendation is determined from the plurality of feature dimension data.
12. A feature recommendation device comprising:
the analysis module is used for responding to a request for abnormal recommendation, analyzing the request and obtaining feature data and a first prediction recommendation result corresponding to the feature data, wherein the feature data comprises a plurality of feature dimension data;
a first determination module to determine one or more alternative feature dimension data corresponding to each of the plurality of feature dimension data;
an obtaining module, configured to respectively process each replacement feature data in a plurality of replacement feature data by using an online recommendation model to obtain a second prediction recommendation result corresponding to each replacement feature data, where the plurality of replacement feature data are obtained based on the feature data and the plurality of replacement feature dimension data; and
and the second determination module is used for determining target feature dimension data which is considered to cause abnormal recommendation from the plurality of feature dimension data according to the first prediction recommendation result and the second prediction recommendation result.
13. The apparatus of claim 12, wherein the first determining means comprises:
the first determining submodule is used for determining a training sample corresponding to the online recommendation model; and
and the first processing submodule is used for processing the training sample corresponding to the online recommendation model to obtain one or more alternative feature dimension data corresponding to each feature dimension data in the plurality of feature dimension data.
14. The apparatus of claim 12 or 13, further comprising:
a generating module, configured to generate the request for abnormal recommendation when it is detected that the first predicted recommendation result satisfies a preset condition,
wherein the preset condition comprises one of:
the predicted recommendation is greater than or equal to a first threshold;
the first predicted recommendation is less than or equal to a second threshold, wherein the second threshold is less than or equal to the first threshold;
a first difference between the first predicted recommendation and the historical recommendation is greater than or equal to a first difference threshold.
15. The apparatus of claim 14, wherein the generating means comprises:
the generation submodule is used for generating the request for abnormal recommendation within a preset time period under the condition that the first prediction recommendation result is detected to meet a preset condition.
16. The apparatus of any of claims 12-15, wherein the request further comprises an online model version identification;
the obtaining module includes:
and the obtaining submodule is used for respectively processing the plurality of replacement characteristic data by using the online recommendation model corresponding to the online model version identification to obtain a second prediction recommendation result corresponding to each replacement characteristic data.
17. The device according to any one of claims 12 to 16, wherein the processing each of the plurality of replacement feature data by using the online recommendation model to obtain the second predicted recommendation corresponding to each replacement feature data is realized by multithreading.
18. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.
19. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-11.
20. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 11.
CN202110663421.2A 2021-06-15 2021-06-15 Data recommendation method, data recommendation device, electronic equipment and readable storage medium Active CN113327133B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110663421.2A CN113327133B (en) 2021-06-15 2021-06-15 Data recommendation method, data recommendation device, electronic equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110663421.2A CN113327133B (en) 2021-06-15 2021-06-15 Data recommendation method, data recommendation device, electronic equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN113327133A true CN113327133A (en) 2021-08-31
CN113327133B CN113327133B (en) 2024-06-21

Family

ID=77420966

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110663421.2A Active CN113327133B (en) 2021-06-15 2021-06-15 Data recommendation method, data recommendation device, electronic equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN113327133B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160371589A1 (en) * 2015-06-17 2016-12-22 Yahoo! Inc. Systems and methods for online content recommendation
CN106383766A (en) * 2016-09-09 2017-02-08 北京百度网讯科技有限公司 System monitoring method and device
CA3055506A1 (en) * 2018-09-18 2020-03-18 10353744 Canada Ltd. Payment method prediction method, payment method prediction apparatus, and computer-readable media
CN111339412A (en) * 2020-02-20 2020-06-26 深圳前海微众银行股份有限公司 Longitudinal federal recommendation recall method, device, equipment and readable storage medium
CN111709810A (en) * 2020-06-17 2020-09-25 腾讯云计算（北京）有限责任公司 Object recommendation method and device based on recommendation model
WO2021004228A1 (en) * 2019-07-08 2021-01-14 汉海信息技术(上海)有限公司 Generation of recommendation reason
CN112785282A (en) * 2021-02-10 2021-05-11 中国工商银行股份有限公司 Resume recommendation method, device, computer system and computer-readable storage medium
CN112836128A (en) * 2021-02-10 2021-05-25 脸萌有限公司 Information recommendation method, device, equipment and storage medium
CN112925978A (en) * 2021-02-26 2021-06-08 北京百度网讯科技有限公司 Recommendation system evaluation method and device, electronic equipment and storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160371589A1 (en) * 2015-06-17 2016-12-22 Yahoo! Inc. Systems and methods for online content recommendation
CN106383766A (en) * 2016-09-09 2017-02-08 北京百度网讯科技有限公司 System monitoring method and device
CA3055506A1 (en) * 2018-09-18 2020-03-18 10353744 Canada Ltd. Payment method prediction method, payment method prediction apparatus, and computer-readable media
WO2021004228A1 (en) * 2019-07-08 2021-01-14 汉海信息技术(上海)有限公司 Generation of recommendation reason
CN111339412A (en) * 2020-02-20 2020-06-26 深圳前海微众银行股份有限公司 Longitudinal federal recommendation recall method, device, equipment and readable storage medium
CN111709810A (en) * 2020-06-17 2020-09-25 腾讯云计算（北京）有限责任公司 Object recommendation method and device based on recommendation model
CN112785282A (en) * 2021-02-10 2021-05-11 中国工商银行股份有限公司 Resume recommendation method, device, computer system and computer-readable storage medium
CN112836128A (en) * 2021-02-10 2021-05-25 脸萌有限公司 Information recommendation method, device, equipment and storage medium
CN112925978A (en) * 2021-02-26 2021-06-08 北京百度网讯科技有限公司 Recommendation system evaluation method and device, electronic equipment and storage medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
DI ZHANG等: "FreshGraph: A Spam-Aware Recommender System for Cold Start Problem", 《2019 IEEE 14TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (ISKE)》, 18 August 2020 (2020-08-18) *
顾军华;李新晨;张亚娟;董彦琦;: "融合标签信息的卷积矩阵分解推荐算法", 计算机应用与软件, no. 03 *
顾军华;李新晨;张亚娟;董彦琦;: "融合标签信息的卷积矩阵分解推荐算法", 计算机应用与软件, no. 03, 12 March 2020 (2020-03-12) *

Also Published As

Publication number Publication date
CN113327133B (en) 2024-06-21

Similar Documents

Publication Publication Date Title
CN114329201A (en) Deep learning model training method, content recommendation method and device
CN114037059A (en) Pre-training model, model generation method, data processing method and data processing device
CN113205189B (en) Method for training prediction model, prediction method and device
CN114461658A (en) Name determination method, apparatus, device, program product, and storage medium
CN113052325A (en) Method, device, equipment, storage medium and program product for optimizing online model
CN114138397B (en) Page display method and device, electronic equipment and storage medium
CN113360672B (en) Method, apparatus, device, medium and product for generating knowledge graph
CN113434432B (en) Performance test method, device, equipment and medium for recommendation platform
CN113612777B (en) Training method, flow classification method, device, electronic equipment and storage medium
CN113327133B (en) Data recommendation method, data recommendation device, electronic equipment and readable storage medium
CN113239273B (en) Method, apparatus, device and storage medium for generating text
CN115454261A (en) Input method candidate word generation method and device, electronic equipment and readable storage medium
CN114912541A (en) Classification method, classification device, electronic equipment and storage medium
CN114218313A (en) Data management method, device, electronic equipment, storage medium and product
CN111416744B (en) Method and device for monitoring and alarming on internet
CN114647768A (en) Notice information acquisition method, device, equipment, medium and product
CN113961797A (en) Resource recommendation method and device, electronic equipment and readable storage medium
CN114036391A (en) Data pushing method and device, electronic equipment and storage medium
CN113362097A (en) User determination method and device
CN113051479A (en) File processing and recommendation information generation method, device, equipment and storage medium
CN112632384A (en) Data processing method and device for application program, electronic equipment and medium
CN113836291B (en) Data processing method, device, equipment and storage medium
CN114299522B (en) Image recognition method device, apparatus and storage medium
CN113344405B (en) Method, device, equipment, medium and product for generating information based on knowledge graph
CN115202791A (en) Method and device for determining first screen loading resource, server and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant