Abstract: A recommendation method, applied to the field of artificial intelligence, includes: obtaining a first feature representation and a second feature representation, where the first feature representation corresponds to attribute information of a target user, the second feature representation corresponds to attribute information of a target item, the first feature representation includes a plurality of first feature sub-representations, and the second feature representation includes a plurality of second feature sub-representations; determining a plurality of similarities based on the plurality of first feature sub-representations and the plurality of second feature sub-representations, where each similarity is a similarity between one of the first feature sub-representations and one of the second feature sub-representations; and fusing the plurality of similarities to obtain recommendation information between the target user and the target item.

Abstract: Embodiments of this application disclose a model training method and a related apparatus, to improve a generalization capability of a prediction model. The method in embodiments of this application includes: calculating a loss function of an error imputation model based on a first error of a prediction result of a prediction model for first sample data, a first output of the error imputation model, and a probability that the first sample data is observed; and then updating a parameter of the error imputation model based on the loss function of the error imputation model, where the first output of the error imputation model represents a predicted value of the first error, the loss function of the error imputation model includes a bias term and a variance term.

Abstract: An operation prediction method includes obtaining a first embedding representation and a second embedding representation of attribute information of a user and an item respectively by using a first feature extraction network and a second feature extraction network. The first embedding representation indicates a feature unrelated to recommendation scenario information. The second embedding representation indicates a feature related to a target recommendation scenario. The first embedding representation and the second embedding representation are used for fusion to obtain a fused embedding representation. The operation prediction method further includes predicting target operation information of the user for the item based on the fused embedding representation.

Abstract: A lightning protection apparatus for a wind generator blade, including a lightning arrester and a lightning arrester base. The lightning arrester includes a connecting portion, a lightning arresting portion, and a positioning portion, wherein the lightning arresting portion is configured to arrest a lightning, an external thread is formed on a surface of the connecting portion and configured to be connected to the lightning arrester base, and the positioning portion is disposed between the connecting portion and the lightning arresting portion, such that after the connecting portion is screwed into a threaded hole, the positioning portion can fit with a recess in the threaded hole in shape. The lightning arrester base is configured to be connected to the lightning arrester and lead out a lightning current received by the lightning arrester during lightning arresting, and includes an insulation layer and at least one the threaded hole.

Abstract: This application discloses an item recommendation method and a related device thereof, so that a probability of tapping an item by the user can be accurately predicted, to improve overall prediction precision of a model. The method in this application includes obtaining first information, where the first information includes attribute information of a user and attribute information of an item. The method also include processing the first information by using a first model to obtain a first processing result, where the first processing result is used to determine the item recommended to the user. Furthermore, the first model is configured to perform a linear operation on the first information to obtain second information, perform a nonlinear operation on the second information to obtain third information, and obtain the first processing result based on the third information.

Abstract: Representation learning methods and related devices are provided. An example method includes: obtaining a dataset of to-be-learned data; inputting the dataset into an encoder, and extracting features of the data segments based on a parameter of the encoder to obtain representation vectors corresponding to data segments of various scales; inputting the representation vectors into an interaction module, and performing, based on a parameter of the interaction module, information interaction on representation vectors corresponding to data segments of adjacent scales in the subset, to obtain fused representation vectors corresponding to the data segments of various scales; constructing an objective function based on the fused representation vectors; and optimizing the objective function to adjust the parameter of the encoder and the parameter of the interaction module, so that the encoder and the interaction module learn a high-quality representation vector of the to-be-learned data.

Abstract: This application relates to the field of fiber-optic communication technologies, and provides a fault locating method, apparatus, and system. The method includes: obtaining a first correspondence between a receive time and receive power during reverse backhaul that occurs when a test optical signal that can be reflected by a reflection component disposed at each port of at least one stage of optical splitter is in downlink transmission in an ODN, where reverse backhaul includes backscatter and reflection or includes backscatter; determining, based on the first correspondence, a second correspondence between a transmission distance and receive power during reverse backhaul that occurs when a test optical signal is in downlink transmission in an optical fiber between each port of the at least one stage of optical splitter and a component connected to the port; and locating a fault in the ODN based on the second correspondence.

Abstract: A method and an apparatus for training a search recommendation model, and a method and an apparatus for sorting search results are provided. The training method includes: obtaining a training sample set including a sample user behavior group sequence and a masked sample user behavior group sequence; and using the training sample set as input data, and training a search recommendation model, to obtain a trained search recommendation model, where a target of the training is to obtain the object of the response operation of the sample user after the mask processing, the search recommendation model is used to predict a label of a candidate recommendation object in search results corresponding to a query field when a target user inputs the query field, and the label is used to indicate a probability that the target user performs a response operation on the candidate recommendation object.

Abstract: A splitter includes an optical input section, N optical branch sections, and at least (N?1) optical filter structures. Each optical filter structure reflects an optical signal of one wavelength. The at least (N?1) optical filter structures include a special optical filter structure and at least (N?3) common optical filter structures, and a wavelength of an optical signal reflected by each of the common optical filter structures is a common wavelength. A wavelength of an optical signal reflected by a first/second special optical filter structure is a first/second special wavelength. At least (N?3) common wavelengths constitute an arithmetic sequence, a difference between the first special wavelength and a largest common wavelength is greater than a tolerance of the arithmetic sequence, and a difference between the second special wavelength and a smallest common wavelength is greater than the tolerance of the arithmetic sequence.

Abstract: This application provides a port identification method, apparatus, and system, and belongs to the field of optical communications technologies. According to this application, a connection relationship between the ONT and the optical splitter and a connection relationship between the ONT and the port of the optical splitter can be accurately identified.

Abstract: This application provides a recommendation model training method in the artificial intelligence (AI) field. The training method includes: obtaining a first training sample; processing attribute information of a first user and information about a first recommended object based on an interpolation model, to obtain an interpolation prediction label of the first training sample; and performing training by using the attribute information of the first user and the information about the first recommended object as an input to a recommendation model and using the interpolation prediction label of the first training sample as a target output value of the recommendation model, to obtain a trained recommendation model. According to the technical solutions of this application, impact of training data bias on recommendation model training can be alleviated, and recommendation model accuracy can be improved.

Abstract: The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.

Abstract: The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.

Abstract: This application provides a port identification method. The method includes: obtaining reflection information of reflection peaks formed by each ONT by separately reflecting test light when the test light provided by a wavelength-tunable device is transmitted in the PON; determining, based on the reflection information of the reflection peaks, a port of a splitter corresponding to each reflection peak group, where each reflection peak group includes reflection peaks formed by a same ONT by reflecting the test light; and determining, based on first transmission information of at least one reflection peak in each reflection peak group, the port of the splitter corresponding to each reflection peak group, and second transmission information between each ONT and an OLT, a port corresponding to each ONT in the splitter. According to this application, port identification efficiency can be improved.

Abstract: This application provides a port identification method, apparatus, and system, and belongs to the field of optical communications technologies. According to this application, a connection relationship between the ONT and the optical splitter and a connection relationship between the ONT and the port of the optical splitter can be accurately identified.

Abstract: Techniques for managing a storage system involve cleaning up a persistent storage disk in a backup mode to increase a writing rate of the persistent storage disk. The techniques further involve creating a library partition in the cleaned persistent storage disk. The techniques further involve writing cache data in a volatile storage device into the library partition. Accordingly, in a storage device with only a single persistent storage disk, cache data in a volatile storage device can be written into the persistent storage disk at a relatively high writing rate, thereby achieving efficient memory persistence.

Abstract: A training method includes: obtaining a first recommendation model, where a model parameter of the first recommendation model is obtained through training based on n first training samples; determining an impact function value of each first training sample with respect to a verification loss of m second training samples in the first recommendation model; determining, based on the impact function value of each first training sample with respect to the verification loss, a weight corresponding to each first training sample; and training the first recommendation model based on the n first training samples and the weights corresponding to the n first training samples, to obtain a target recommendation model.

Abstract: A splitter includes an optical input section, N optical branch sections, and at least (N?1) optical filter structures. Each optical filter structure reflects an optical signal of one wavelength. The at least (N?1) optical filter structures include a special optical filter structure and at least (N?3) common optical filter structures, and a wavelength of an optical signal reflected by each of the common optical filter structures is a common wavelength. A wavelength of an optical signal reflected by a first/second special optical filter structure is a first/second special wavelength. At least (N?3) common wavelengths constitute an arithmetic sequence, a difference between the first special wavelength and a largest common wavelength is greater than a tolerance of the arithmetic sequence, and a difference between the second special wavelength and a smallest common wavelength is greater than the tolerance of the arithmetic sequence.

Abstract: A method and an apparatus for training a search recommendation model, and a method and an apparatus for sorting search results are provided. The training method includes: obtaining a training sample set including a sample user behavior group sequence and a masked sample user behavior group sequence; and using the training sample set as input data, and training a search recommendation model, to obtain a trained search recommendation model, where a target of the training is to obtain the object of the response operation of the sample user after the mask processing, the search recommendation model is used to predict a label of a candidate recommendation object in search results corresponding to a query field when a target user inputs the query field, and the label is used to indicate a probability that the target user performs a response operation on the candidate recommendation object.

Abstract: A recommendation method includes generating a feature sequence based on to-be-predicted data of a user for a target object and according to a preset encoding rule, obtaining probability distribution information corresponding to each feature in the feature sequence, and obtaining, through calculation, a feature vector corresponding to each feature, obtaining a predicted score of the user for the target object based on values of N features and a feature vector corresponding to each of the N features, and recommending the target object to the user when the predicted score is greater than or equal to a preset threshold.