Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.

Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.

Sub-systems of air handling units in infrastructures face unresolved problem of conflict in the rules that activate in a contradictory manner at the same time resulting in sub-optimal performance of the subsystems. The present disclosure provides a system and method for optimizing performance parameters of air handling units in infrastructures. Rule sets having conflicting conditions are identified after verification of rules which are specific to air handling units. Further, frequency of the rule sets having conflicting conditions is determined to generate a ranked list of the rule sets having conflicting conditions. Another ranking procedure is implemented for the rules comprised in the ranked list of the rule sets having conflicting conditions. The system dynamically optimizes one or more parameters specific to the performance criteria based on the ranking of rules.

The embodiment of the present disclosure provides a question-and-answer processing method, including: acquiring a to-be-answered question; determining standard questions meeting a preset condition as a plurality of candidate standard questions, from a plurality of preset standard questions, according to a text similarity with the to-be-answered question, based on a text statistical algorithm; determining, a candidate standard question with the highest semantic similarity with the to-be-answered question as a matching standard question, from the plurality of candidate standard questions, based on a deep text matching algorithm; and determining an answer to the to-be-answered question at least according to the matching standard question. The embodiment of the present disclosure also provides an electronic device and a computer readable medium.

The embodiment of the present disclosure provides a question-and-answer processing method, including: acquiring a to-be-answered question; determining standard questions meeting a preset condition as a plurality of candidate standard questions, from a plurality of preset standard questions, according to a text similarity with the to-be-answered question, based on a text statistical algorithm; determining, a candidate standard question with the highest semantic similarity with the to-be-answered question as a matching standard question, from the plurality of candidate standard questions, based on a deep text matching algorithm; and determining an answer to the to-be-answered question at least according to the matching standard question. The embodiment of the present disclosure also provides an electronic device and a computer readable medium.

The present invention is a combined commodity mining method based on knowledge graph rule embedding, comprising: expressing rules, commodities, attributes, and attribute values as embeddings; splicing and inputting the embeddings of the rules and the embeddings of the attributes into a first neural network to obtain a importance scores of the attributes; splicing and inputting the rules and attributes into a second neural network to obtain the embeddings of the attribute values that the rules should take under the attributes; calculating a similarity between the value of two inputted commodities under the attribute and the embedding of the attribute value calculated by a model; after calculating scores of all attribute-attribute value pairs, summing up to obtain scores of these two commodities under this rule; then making the cross entropy loss with the real scores of these two commodities, and iteratively training based on an optimization algorithm having gradient descent; after the model is trained, parsing the embeddings of the rules in a similar way to obtain rules that can be understood by human beings.

A disease prediction method, apparatus, and computer program are provided. A disease prediction method according to several embodiments of the present disclosure can comprise the steps of: constructing a disease prediction model by learning learning data including ribosome data and disease information for learning, acquiring test ribosome data of an examinee; and predicting disease information about the examinee form the test ribosome data by using the disease prediction model. The disease prediction model can accurately predict disease information about the examinee by detecting and learning the characteristics of ribosome data, which vary according to disease information.

A non-transitory computer-readable storage medium storing an explanatory information output program for causing a computer to execute processing includes obtaining a contribution of each of a plurality of factors to an output result of a machine learning model in a case of inputting each of a plurality of pieces of data, each of the plurality of factors being included in each of the plurality of pieces of data; clustering the plurality of pieces of data based on the contribution of each of the plurality of factors to generate a plurality of groups of factors; and outputting explanatory information that includes a diagram representing magnitude of the contribution of each of the plurality of factors to the output result in a case of inputting data included in the group for each of the plurality of groups.

Aspects described herein utilize a resource management model and a resource utilization model, such that simulations may be performed accordingly. For example, a resource management time period may be a timeframe during which resource management is simulated according to the resource management model, while a resource utilization time period may be the timeframe in which resource utilization is simulated. Optimizing a resource allocation based on such simulations may be computationally expensive, for example due to the number of simulation iterations associated with each optimization iteration. Accordingly, a simulation may utilize one or more gates, which may identify a simulation state that is indicative of a degraded optimization iteration. When such a sub-optimal iteration is identified, the simulation may be interrupted and a subsequent optimization iteration may be simulated instead. Thus, processing time may be reduced for iterations that are unlikely to ultimately result in an optimized resource allocation.

Aspects described herein utilize a resource management model and a resource utilization model, such that simulations may be performed accordingly. For example, a resource management time period may be a timeframe during which resource management is simulated according to the resource management model, while a resource utilization time period may be the timeframe in which resource utilization is simulated. Optimizing a resource allocation based on such simulations may be computationally expensive, for example due to the number of simulation iterations associated with each optimization iteration. Accordingly, a simulation may utilize one or more gates, which may identify a simulation state that is indicative of a degraded optimization iteration. When such a sub-optimal iteration is identified, the simulation may be interrupted and a subsequent optimization iteration may be simulated instead. Thus, processing time may be reduced for iterations that are unlikely to ultimately result in an optimized resource allocation.