A method for generating a target function is provided. The method includes: performing normalization processing on a vector corresponding to each pixel in a target feature map set to generate a target vector, so as to obtain a target vector set; generating hash coding corresponding to each vector in the target vector set, to obtain a hash coding set; determining a prior probability of each hash coding in the hash coding set; and generating a target function based on an entropy of the prior probability.

A method for generating a target function is provided. The method includes: performing normalization processing on a vector corresponding to each pixel in a target feature map set to generate a target vector, so as to obtain a target vector set; generating hash coding corresponding to each vector in the target vector set, to obtain a hash coding set; determining a prior probability of each hash coding in the hash coding set; and generating a target function based on an entropy of the prior probability.

A first standard deviation of feature quantities of all pieces of non-expert data stored in a non-expert data storage unit 13 is calculated, and a second standard deviation of feature quantities of all pieces of expert data stored in an expert data storage unit 14 is calculated. In addition, a first rank sum of the feature quantities of all pieces of non-expert data stored in the non-expert data storage unit 13 is calculated, and a second rank sum of the feature quantities of all pieces of expert data stored in the expert data storage unit 14 is calculated. Then, a continuation and an end of acquisition of defective product data by an expert are determined, based on the first standard deviation and the second standard deviation , and the first rank sum and the second rank sum .

A first standard deviation of feature quantities of all pieces of non-expert data stored in a non-expert data storage unit 13 is calculated, and a second standard deviation of feature quantities of all pieces of expert data stored in an expert data storage unit 14 is calculated. In addition, a first rank sum of the feature quantities of all pieces of non-expert data stored in the non-expert data storage unit 13 is calculated, and a second rank sum of the feature quantities of all pieces of expert data stored in the expert data storage unit 14 is calculated. Then, a continuation and an end of acquisition of defective product data by an expert are determined, based on the first standard deviation and the second standard deviation , and the first rank sum and the second rank sum .

A method and system for intelligent monitoring of equipment damage based on mechanism and operating condition big data are provided. The method includes: setting damage modes of pressure equipment, building mechanism model samples for each damage mode based on a technical standard and engineering cases, building operating condition big data samples for the each damage mode based on field data; building a mechanism model and an operating condition model based on the mechanism model samples and the operating condition big data samples respectively; inputting real-time text data and real-time operating condition data into the mechanism model and the operating condition model respectively, calculating a first possibility that the real-time text data belongs to each damage mode, and a second possibility that the real-time operating condition data belongs to the each damage mode, generating an equipment damage monitoring result based on the first possibility and the second possibility.

A method and system for intelligent monitoring of equipment damage based on mechanism and operating condition big data are provided. The method includes: setting damage modes of pressure equipment, building mechanism model samples for each damage mode based on a technical standard and engineering cases, building operating condition big data samples for the each damage mode based on field data; building a mechanism model and an operating condition model based on the mechanism model samples and the operating condition big data samples respectively; inputting real-time text data and real-time operating condition data into the mechanism model and the operating condition model respectively, calculating a first possibility that the real-time text data belongs to each damage mode, and a second possibility that the real-time operating condition data belongs to the each damage mode, generating an equipment damage monitoring result based on the first possibility and the second possibility.

In an embodiment, there is provided a self-supervised representation learning (SSRL) circuitry. The SSRL circuitry includes a normalizer circuitry, and a loss function circuitry. The normalizer circuitry is configured to receive a number. T, batches of embedding features. Each batch includes a number. N, embedding features. The number N corresponds to a number of input samples in a training batch. The number T corresponds to a number of respective transformed batches. Each transformed batch corresponds to a respective transformation of the training batch. The embedding features may be related to the transformed batches. Each embedding feature has a dimension. D. and each embedding feature element corresponds to a respective feature variable. The normalizer circuitry is further configured to normalize each feature variable of a selected batch, using a zero mean and a unit standard deviation of the selected batch. A loss function circuitry is configured to determine a loss function based, at least in part, on a factorizable mixed moment of a plurality of normalized feature variables. The mixed moment is of order K. K is less than or equal to the embedding feature dimension D.

In an embodiment, there is provided a self-supervised representation learning (SSRL) circuitry. The SSRL circuitry includes a normalizer circuitry, and a loss function circuitry. The normalizer circuitry is configured to receive a number. T, batches of embedding features. Each batch includes a number. N, embedding features. The number N corresponds to a number of input samples in a training batch. The number T corresponds to a number of respective transformed batches. Each transformed batch corresponds to a respective transformation of the training batch. The embedding features may be related to the transformed batches. Each embedding feature has a dimension. D. and each embedding feature element corresponds to a respective feature variable. The normalizer circuitry is further configured to normalize each feature variable of a selected batch, using a zero mean and a unit standard deviation of the selected batch. A loss function circuitry is configured to determine a loss function based, at least in part, on a factorizable mixed moment of a plurality of normalized feature variables. The mixed moment is of order K. K is less than or equal to the embedding feature dimension D.

Systems and methods are disclosed comprising techniques for record-to-event conversion, such as retrieving at least one alphanumeric record associated with a monitored digital communication transmitted among two or more users, generating a time-enumerated data structure that stores an event entry set for the monitored digital communication, selectively identifying at least one discrete event for the monitored digital communication, generating one or more relevance scores for the at least one discrete event, identifying at least one valid discrete event from the at least one discrete event, generating an event attribute set for the at least one valid discrete event, updating the normalized event attribute set for a new event entry within the event entry set of the time-enumerated data structure, and transmitting the updated time-enumerated data structure within an elapsed duration after retrieving the at least one alphanumeric record.

Systems and methods are disclosed comprising techniques for record-to-event conversion, such as retrieving at least one alphanumeric record associated with a monitored digital communication transmitted among two or more users, generating a time-enumerated data structure that stores an event entry set for the monitored digital communication, selectively identifying at least one discrete event for the monitored digital communication, generating one or more relevance scores for the at least one discrete event, identifying at least one valid discrete event from the at least one discrete event, generating an event attribute set for the at least one valid discrete event, updating the normalized event attribute set for a new event entry within the event entry set of the time-enumerated data structure, and transmitting the updated time-enumerated data structure within an elapsed duration after retrieving the at least one alphanumeric record.