Information processing method, temperature prediction model training method, device and electronic equipment

Abstract

The present disclosure is about an information processing method, a temperature prediction model training method, a device and an electronic device, and the method includes: obtaining the real-time operating parameters of a target server in a target environment; inputting the real-time operating parameters into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; when the target predicted temperature corresponding to the target server is greater than a temperature threshold, generating temperature warning information for the target server based on the target predicted temperature corresponding to the target server. It can be seen that by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, measures can be taken in time in advance to ensure the safe operation of the target server.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing, and in particular to an information processing method, a temperature prediction model training method, a device and an electronic device. Background Art

[0002] With the advent of the Internet era, the scale and number of data centers are becoming very large. Servers are the main components of data centers, and ensuring the stable operation of servers is the key to data center operation and maintenance.

[0003] A large amount of heat is generated during the operation of the server, which will increase the surrounding temperature. Therefore, in the related art, the computer room of the data center is generally equipped with air conditioning and refrigeration equipment and air circulation systems to control the temperature of the computer room, so that the temperature of the computer room is always kept below the industry safety temperature red line (for example, 35 degrees Celsius) for server operation.

[0004] Servers are installed in the computer room in cabinets, and circulating cooling air circulates between the cabinets. When the temperature exceeds the industry temperature red line, the computer room management system will issue a temperature control failure alarm. At the same time, in order to detect server operating temperature failures early, most computer rooms have set up a temperature baseline. When the cabinet temperature sensor finds that the temperature around the server exceeds 31 degrees, it will issue an early warning. Because the server temperature often fluctuates between the baseline and the red line, it cannot be distinguished from the temperature breaking caused by a failure, which often leads to false alarms. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the present disclosure provides an information processing method, a temperature prediction model training method, a device and an electronic device.

[0006] According to a first aspect of an embodiment of the present disclosure, there is provided an information processing method, including:

[0007] Obtain the real-time operating parameters of the target server in the target environment;

[0008] The real-time operating parameters are input into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; wherein the temperature prediction model includes a first sub-model and a second sub-model, the first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain a first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0009] When the target predicted temperature corresponding to the target server is greater than a temperature threshold, temperature warning information for the target server is generated based on the target predicted temperature corresponding to the target server.

[0010] Optionally, the method further includes:

[0011] Determining the correlation between the servers according to the historical operating temperatures of the servers and the corresponding target predicted temperatures;

[0012] Based on the server identification of each server and the size of the correlation between the servers, a correlation graph network is constructed, wherein the correlation graph network includes multiple nodes, the node identification of each node corresponds to the server identification of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the size of the correlation between the servers corresponding to the two nodes.

[0013] Optionally, determining the correlation between the servers according to the historical operating temperatures of the servers and the corresponding target predicted temperatures includes:

[0014] Determine, according to the historical operating temperature of each server and the corresponding target predicted temperature, an event corresponding to each server, wherein the event is used to describe a change relationship between the historical operating temperature of each server and the corresponding target predicted temperature;

[0015] For each server, count the number of events that occur at the same time with each other service;

[0016] For each server, the correlation between the server and other servers is determined based on the number of identical events occurring between the server and other servers, wherein the correlation is proportional to the number of identical events occurring.

[0017] Optionally, the method further includes:

[0018] When it is detected that the correlation graph network has a first target node, a second target node whose correlation with the first target node is greater than a preset correlation is obtained, and a target predicted temperature of a server corresponding to the first target node is greater than the temperature threshold;

[0019] Determine the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold;

[0020] When the number of nodes is greater than a preset number, temperature warning information of the server corresponding to the first target node and the server corresponding to the second target node is generated.

[0021] In a second aspect, an embodiment of the present disclosure provides a method for training a temperature prediction model, wherein the temperature prediction model includes a first sub-model and a second sub-model, including:

[0022] Obtaining historical operating parameters of each server in the target environment and historical operating temperatures of each server;

[0023] The first sub-model is trained using the historical operating parameters of each server and the historical operating temperature of each server to obtain a first predicted temperature corresponding to each server;

[0024] The second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0025] Determining a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server;

[0026] When the loss function value is less than a preset loss value, it is determined that a trained temperature prediction model is obtained.

[0027] Optionally, the training the second sub-model by using the first predicted temperature of each server and the historical operating temperature of each server includes:

[0028] For each server, a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server are combined into a first key-value pair;

[0029] Determining the first key-value pair as a training sample;

[0030] The training samples are input into the second sub-model to train the second sub-model.

[0031] Optionally, inputting the training sample into the second sub-model to train the second sub-model includes:

[0032] Sorting the plurality of first key-value pairs according to the values ​​of the first predicted temperatures in the first key-value pairs to obtain sorted first key-value pairs;

[0033] Divide the sorted first key-value pairs into buckets, and obtain the average of the historical operating temperatures in the first key-value pairs in each bucket;

[0034] For each sorted first key-value pair, the first predicted temperature in the first key-value pair and the average value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair;

[0035] The second key-value pair is input into the second sub-model to train the second sub-model; wherein the first predicted temperature in the second key-value pair is a feature value, and the mean value in the second key-value pair is a label.

[0036] In a third aspect, an embodiment of the present disclosure provides an information processing device, including:

[0037] An operation parameter acquisition module is configured to execute and acquire real-time operation parameters of a target server in a target environment;

[0038] The temperature prediction module is configured to execute inputting the real-time operating parameters into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; wherein the temperature prediction model includes a first sub-model and a second sub-model, the first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain a first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0039] The first temperature warning information generating module is configured to generate temperature warning information for the target server based on the target predicted temperature corresponding to the target server when the target predicted temperature corresponding to the target server is greater than a temperature threshold.

[0040] Optionally, the device further comprises:

[0041] A correlation determination module is configured to determine the correlation between the servers according to the historical operating temperature of the servers and the corresponding target predicted temperature;

[0042] The graph network construction module is configured to construct a correlation graph network based on the server identifications of the servers and the correlation sizes between the servers, wherein the correlation graph network includes multiple nodes, the node identification of each node corresponds to the server identification of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the correlation size between the servers corresponding to the two nodes.

[0043] Optionally, the correlation determination module is specifically configured to execute:

[0044] Determine, according to the historical operating temperature of each server and the corresponding target predicted temperature, an event corresponding to each server, wherein the event is used to describe a change relationship between the historical operating temperature of each server and the corresponding target predicted temperature;

[0045] For each server, count the number of events that occur at the same time with each other service;

[0046] For each server, the correlation between the server and other servers is determined based on the number of identical events occurring between the server and other servers, wherein the correlation is proportional to the number of identical events occurring.

[0047] Optionally, the device further comprises:

[0048] A node acquisition module is configured to execute, when detecting that a first target node exists in the correlation graph network, acquiring a second target node whose correlation with the first target node is greater than a preset correlation, and a target predicted temperature of a server corresponding to the first target node is greater than the temperature threshold;

[0049] A node determination module is configured to determine the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold;

[0050] The second temperature warning information generating module is configured to generate temperature warning information of a server corresponding to the first target node and a server corresponding to the second target node when the number of nodes is greater than a preset number.

[0051] In a fourth aspect, an embodiment of the present disclosure provides a temperature prediction model training device, wherein the temperature prediction model includes a first sub-model and a second sub-model, including:

[0052] A historical data acquisition module is configured to acquire historical operating parameters of each server in the target environment and historical operating temperatures of each server;

[0053] A first sub-model training module is configured to train the first sub-model using the historical operating parameters of each server and the historical operating temperature of each server to obtain a first predicted temperature corresponding to each server;

[0054] A second sub-model training module is configured to train the second sub-model using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0055] A loss function value determination module, configured to determine a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server;

[0056] The temperature prediction model determination module is configured to determine the trained temperature prediction model when the loss function value is less than a preset loss value.

[0057] Optionally, the second sub-model training module includes:

[0058] A key-value pair determining unit is configured to execute, for each server, combining a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server into a first key-value pair;

[0059] A training sample determining unit, configured to determine the first key-value pair as a training sample;

[0060] The second sub-model training unit is configured to input the training sample into the second sub-model to train the second sub-model.

[0061] Optionally, the second sub-model training unit is specifically configured to execute:

[0062] Sorting the plurality of first key-value pairs according to the values ​​of the first predicted temperatures in the first key-value pairs to obtain sorted first key-value pairs;

[0063] Divide the sorted first key-value pairs into buckets, and obtain the average of the historical operating temperatures in the first key-value pairs in each bucket;

[0064] For each sorted first key-value pair, the first predicted temperature in the first key-value pair and the average value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair;

[0065] The second key-value pair is input into the second sub-model to train the second sub-model; wherein the first predicted temperature in the second key-value pair is a feature value, and the mean value in the second key-value pair is a label.

[0066] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0067] processor;

[0068] a memory for storing processor-executable instructions;

[0069] Wherein, the processor is configured to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect.

[0070] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the electronic device to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect.

[0071] In a seventh aspect, an embodiment of the present disclosure provides a computer program product, which, when executed on a computer, enables the computer to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect.

[0072] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0073] The technical solution provided by the embodiment of the present disclosure obtains the real-time operating parameters of the target server in the target environment; inputs the real-time operating parameters into the pre-trained temperature prediction model to obtain the target predicted temperature corresponding to the target server; when the target predicted temperature corresponding to the target server is greater than the temperature threshold, generates temperature warning information for the target server based on the target predicted temperature corresponding to the target server. Since the temperature prediction model is trained with a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, measures can be taken in time in advance to ensure the safe operation of the target server.

[0074] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0076] Figure 1 is a flow chart of an information processing method according to an exemplary embodiment;

[0077] Figure 2 is a flow chart showing another information processing method according to an exemplary embodiment;

[0078] Figure 3 yes Figure 1 A flowchart of an implementation of step S140;

[0079] Figure 4 It is a schematic diagram of the changing relationship between the historical operating temperature and the corresponding target predicted temperature;

[0080] Figure 5 is a flow chart showing another information processing method according to an exemplary embodiment;

[0081] Figure 6is a flow chart of a temperature prediction model training method according to an exemplary embodiment;

[0082] Figure 7 yes Figure 6 A flowchart of an implementation of step S630;

[0083] Figure 8 yes Figure 7 A flowchart of an implementation of step S633;

[0084] Fig. 9 is a block diagram of an information processing device according to an exemplary embodiment;

[0085] Fig.10 is a block diagram of a temperature prediction model training device according to an exemplary embodiment;

[0086] Fig.11 is a block diagram of an electronic device according to an exemplary embodiment;

[0087] Fig.12 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0088] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0089] In order to solve the problem of false alarm of server temperature existing in the related art, the embodiments of the present disclosure provide an information processing method, a temperature prediction model training method, a device and an electronic device.

[0090] In the first aspect, an information processing method provided by an embodiment of the present disclosure is first described in detail.

[0091] Figure 1 is a flowchart of an information processing method according to an exemplary embodiment. Figure 1 As shown, the method is used in a terminal and may include the following steps:

[0092] In step S110, real-time operating parameters of the target server in the target environment are obtained.

[0093] The target environment in the embodiment of the present disclosure may be a space area including multiple servers, such as a computer room, a cabinet, etc. In practical applications, the target environment may also include refrigeration equipment. The target server may be any server included in the target environment.

[0094] Among them, the operating parameters of the target server may include CPU usage, DISK usage, DISK read and write speed, Memory read and write speed, network transmission speed and refrigeration equipment output power, etc., which are not specifically limited in the embodiments of the present disclosure.

[0095] In step S120, the real-time operating parameters are input into the pre-trained temperature prediction model to obtain the target predicted temperature corresponding to the target server.

[0096] Among them, the temperature prediction model includes a first sub-model and a second sub-model. The first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain the first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain the target predicted temperature corresponding to each server.

[0097] In the disclosed embodiment, the historical operating parameters of each server collected in the historical time period are obtained; and the historical operating temperature of the server collected by the server sensor is obtained, and the historical operating parameters of each server are used as the features of the first sub-model, and the collected historical operating temperature of each server is used as a label to train the first sub-model, and the first sub-model outputs a first predicted temperature. In the embodiment, the operating parameters of each server in the last month or a few days can be determined as the historical operating parameters. Of course, it can be determined according to actual needs and is not limited here.

[0098] It is understandable that although the first sub-model after training can output the first predicted temperature, the first sub-model trained only by the historical operating parameters and the historical operating temperature is often not able to accurately predict the temperature. Therefore, in this embodiment, a second sub-model is set, and the second sub-model is trained by the first predicted temperature of each server output by the first sub-model and the historical operating temperature of each server. When training the second sub-model, the first predicted temperature is used as a feature and the historical operating temperature is used as a label. After the first sub-model and the second sub-model are trained, a temperature prediction model composed of the first sub-model and the second sub-model is obtained.

[0099] Since the historical operating temperature is the actual temperature of the server during operation collected by the server sensor, by training the first sub-model and the second sub-model, the predicted temperature output by the temperature prediction model can be closer to the actual temperature of the server operation, so that the trained temperature prediction model can more accurately predict the temperature of the target server.

[0100] In the embodiment, both the first sub-model and the second sub-model can use XGboost, which has higher accuracy and faster running time, as the model. For example, the first XGboost model is trained by the historical operating parameters and historical operating temperatures of each server in the past three months. The second XGboost model is trained by the first predicted temperature and the historical operating temperature to obtain a temperature prediction model.

[0101] In order to make the description of the scheme complete and clear, the specific training process of the temperature prediction model will be described in detail in the following embodiments.

[0102] In step S130, when the target predicted temperature corresponding to the target server is greater than the temperature threshold, temperature warning information for the target server is generated based on the target predicted temperature corresponding to the target server.

[0103] After obtaining the target predicted temperature corresponding to the target server, if the target predicted temperature is greater than the temperature threshold, it means that the target predicted temperature corresponding to the target server is high, and temperature warning information for the target server is generated so that relevant measures can be taken in time to ensure the safe operation of the target server.

[0104] The temperature threshold may be set according to actual conditions, and the embodiments of the present disclosure do not specifically limit this.

[0105] The technical solution provided by the embodiment of the present disclosure obtains the real-time operating parameters of the target server in the target environment; inputs the real-time operating parameters into the pre-trained temperature prediction model to obtain the target predicted temperature corresponding to the target server; when the target predicted temperature corresponding to the target server is greater than the temperature threshold, generates temperature warning information for the target server based on the target predicted temperature corresponding to the target server. Since the temperature prediction model is trained with a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, measures can be taken in time in advance to ensure the safe operation of the target server.

[0106] exist Figure 1 Based on the embodiment shown, Figure 2 As shown, the information processing method may also include the following steps:

[0107] S140, determining the correlation between the servers according to the historical operating temperature of each server and the corresponding target predicted temperature.

[0108] Specifically, after obtaining the historical operating temperature and target predicted temperature of each server, the correlation between any two servers can be determined based on the change trends of the historical operating temperature and the target predicted temperature, as well as the size relationship between the historical operating temperature and the target predicted temperature. For example, if the change trends of the historical operating temperature and the target predicted temperature of two servers are the same, it can be determined that the correlation between the two servers is large. Otherwise, the correlation between the two servers is small.

[0109] In order to make the description of the solution complete and clear, the specific implementation of S140 will be described in detail in the following embodiments.

[0110] S150: construct a correlation graph network based on the server identifiers of the servers and the correlation sizes between the servers.

[0111] The correlation graph network includes multiple nodes, the node identifier of each node corresponds to the server identifier of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the correlation between the servers corresponding to the two nodes.

[0112] Specifically, each server can be regarded as a node to establish a network topology. Based on the air velocity and air flow path, it can be roughly estimated that the time required for the air of the refrigeration equipment to circulate once is 24 seconds. The predicted operating temperature of each server can be sliced ​​according to 24 seconds, and the key-value pair (node ​​identifier, event) of each node is obtained, and a graph network is constructed based on this. For example, 15*3600*3000 pieces of data can be obtained by collecting data from 15 computer rooms for 15 days for a total of 15*24h and predicting the temperature of 3000 nodes.

[0113] Furthermore, the weight of the edge connecting the two nodes can be determined based on the correlation between any two nodes, and the greater the correlation, the greater the weight.

[0114] It can be seen that through this implementation, a correlation graph network is established, and then the correlation between any two servers is obtained, so that in the subsequent steps, when the temperature of one server is abnormal, early warning information is generated that other servers with higher correlation are also abnormal.

[0115] exist Figure 2 Based on the embodiment shown, in another embodiment provided by the present disclosure, as Figure 3As shown, S140 may include the following steps:

[0116] In S141 , an event corresponding to each server is determined according to the historical operating temperature of each server and the corresponding target predicted temperature.

[0117] The event is used to describe the changing relationship between the historical operating temperature of each server and the corresponding target predicted temperature.

[0118] Specifically, the time corresponding to each server can be judged from two aspects: the first is whether the temperature change trend T is correct, and the second is whether the temperature value V is correct. Generally speaking, it can be summarized into three events:

[0119] 1. Same T, different V: Often the waveforms are the same and the variances are close, but the true value, i.e. the historical operating temperature, is often higher / lower than the corresponding standard predicted temperature, such as Figure 4 a.

[0120] 2. Different T, same V: It is often manifested as similar means, but the corresponding standard predicted temperature fluctuates around the true value, that is, the historical operating temperature, or the true value, that is, the historical operating temperature, fluctuates around the target predicted temperature, and the variance of the two is quite different, such as Figure 4 b.

[0121] 3. T and V are different: It is often manifested that the long-term trend of the real value, that is, the historical operating temperature and the target predicted temperature are opposite, resulting in a large difference in the mean and variance. Figure 4 c.

[0122] In S142, for each server, the number of the same events occurring at the same time with other services is calculated.

[0123] After determining the events that occur on each server at each moment, the number of the same events that occur on each server at each moment with other servers can be counted.

[0124] In S143, for each server, the correlation between the server and other servers is determined based on the number of identical events that occur between the server and other servers.

[0125] The size of the correlation is proportional to the number of identical events that occur.

[0126] It is understandable that the more the number of identical events sent by two servers at the same time is, the more similar the two servers are, that is, the greater the correlation between the two servers is. On the contrary, the fewer the number of identical events sent by two servers at the same time is, the lower the similarity between the two servers is, that is, the smaller the correlation between the two servers is.

[0127] It can be seen that, through the technical solution provided by this embodiment, the correlation between any two servers can be accurately determined through the change relationship between the historical operating temperature of each server and the corresponding target predicted temperature.

[0128] exist Figure 3 Based on the embodiment shown, Figure 5 As shown, the method may also include the following steps:

[0129] In S510, when it is detected that a first target node exists in a plurality of nodes, a second target node whose correlation with the first target node is greater than a preset correlation is acquired.

[0130] The target predicted temperature of the server corresponding to the first target node is greater than the temperature threshold.

[0131] Specifically, when the early warning system finds that the temperature of a server node is abnormal and needs an early warning through the temperature prediction model, it will further calculate the nodes with high correlation with the current node. The preset correlation can be determined according to the actual situation and is not specifically limited here.

[0132] In S520, the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold is determined.

[0133] After discovering that the node temperature of a server is abnormal, it is determined whether the server corresponding to the node with high correlation with the node has an abnormality, that is, whether the target predicted temperature corresponding to the server with high correlation is greater than the temperature threshold. And the number of nodes in the second target node whose corresponding server's target predicted temperature is greater than the temperature threshold is counted.

[0134] In S530, when the number of nodes is greater than a preset number, temperature warning information of a server corresponding to the first target node and a server corresponding to the second target node is generated.

[0135] Specifically, when the number of nodes is greater than a preset number, it indicates that a large proportion of servers with high correlation also send temperature anomalies, which is judged as a group temperature anomaly event. This method effectively implements group temperature anomaly warning.

[0136] The disclosed embodiment improves the prediction accuracy based on the existing temperature prediction model, and through monitoring and recording the historical operating temperature results, builds a server temperature correlation graph network offline, and obtains a "cluster" with high correlation in temperature events for each node through the graph network and temperature correlation calculation, realizes group alarm from the perspective of various types of server groups and group cabinets, and can reduce false alarms.

[0137] In the second aspect, a temperature prediction model training method provided by an embodiment of the present disclosure is elaborated in detail.

[0138] The temperature prediction model provided by the embodiment of the present disclosure includes a first sub-model and a second sub-model.

[0139] like Figure 6 As shown, a temperature prediction model training method provided by an embodiment of the present disclosure may include the following steps:

[0140] S610: Obtain historical operating parameters and historical operating temperatures of each server in the target environment.

[0141] The target environment in the embodiment of the present disclosure may be a space area including multiple servers, such as a computer room, a cabinet, etc. In practical applications, the target environment may also include refrigeration equipment. The target server may be any server included in the target environment.

[0142] Among them, the operating parameters of each server may include CPU usage, DISK usage, DISK read and write speed, Memory read and write speed, network transmission speed and refrigeration equipment output power, etc., which are not specifically limited in the embodiments of the present disclosure.

[0143] The historical operating temperature of each server may be a temperature collected by a sensor of the server.

[0144] S620: Train the first sub-model using the historical operating parameters and the historical operating temperatures of each server to obtain a first predicted temperature corresponding to each server.

[0145] When training the first sub-model, the historical operating parameters of each server can be used as the features of the first sub-model, and the collected historical operating temperatures of each server can be used as labels. The output of the first sub-model is the first predicted temperature. In other words, the first sub-model learns the relationship between the historical operating parameters and the temperature.

[0146] S630: Train the second sub-model using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server.

[0147] It is understandable that although the trained first sub-model can output the first predicted temperature, the first sub-model trained only by the historical operating parameters and the historical operating temperature is often not able to accurately predict the temperature. Therefore, in this embodiment, a second sub-model is set, and the second sub-model is trained by the first predicted temperature of each server output by the first sub-model and the historical operating temperature of each server. When training the second sub-model, the first predicted temperature is used as a feature and the historical operating temperature is used as a label.

[0148] In the embodiment, both the first sub-model and the second sub-model can use XGboost, which has higher accuracy and faster running time, as the model. For example, the first XGboost model is trained by the historical operating parameters and historical operating temperatures of each server in the past three months. The second XGboost model is trained by the first predicted temperature and the historical operating temperature to obtain a temperature prediction model.

[0149] S640: Determine a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server.

[0150] After obtaining the target predicted temperature corresponding to each server, the loss value of the temperature prediction model can be determined by calculating the sum square error, mean square error, etc. between the target predicted temperature and the historical operating temperature of the server. The embodiments of the present disclosure do not specifically limit this.

[0151] S650: When the loss function value is less than a preset loss value, determine to obtain a trained temperature prediction model.

[0152] Specifically, if the loss function value is less than the preset loss value, it means that the target predicted temperature is close to the corresponding historical operating temperature, that is, the temperature prediction model can accurately predict the operating temperature of each server. Therefore, the trained temperature prediction model is determined.

[0153] On the contrary, if the loss function value is greater than the preset loss value, it means that the target predicted temperature is significantly different from the corresponding historical operating temperature, that is, the accuracy of the temperature prediction model in predicting the operating temperature of each server is low. Therefore, it is necessary to continue training the temperature prediction model.

[0154] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0155] based on Figure 6 In order to elaborate on how to train the second sub-model, in another embodiment provided by the present disclosure, Figure 7 As shown, step S630 may include the following steps:

[0156] Step S631: for each server, a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server are combined into a first key-value pair.

[0157] Step S632: determine the first key-value pair as a training sample.

[0158] Step S633: input the training sample into the second sub-model to train the second sub-model.

[0159] In this embodiment, by using the first predicted temperature as a feature and the historical operating temperature as a label, the predicted temperature output from the second sub-model, namely the temperature prediction model, can be closer to the historical operating temperature, so that the temperature prediction model can more accurately predict the temperature of the target server.

[0160] exist Figure 7 Based on the above embodiment, in one implementation, in step S633, the training sample is input into the second sub-model to train the second sub-model, such as Figure 8 As shown, the following steps may be included:

[0161] In step S6331, a plurality of first key-value pairs are sorted according to the numerical value of the first predicted temperature in the first key-value pair to obtain sorted first key-value pairs.

[0162] In this embodiment, the second sub-model is trained by order-preserving regression. Specifically, after N first predicted values ​​and historical operating temperatures are matched to form N first key-value pairs, the first key-value pairs can be sorted according to the first predicted values. The sorting can be to arrange the real values ​​close to the first predicted values ​​into monotonically increasing or decreasing data as adjacent values ​​close to the linear path.

[0163] In step S6332, the sorted first key-value pairs are bucketed, and the average of the historical operating temperatures in the first key-value pairs in each bucket is obtained.

[0164] In step S6333, for each sorted first key-value pair, the first predicted temperature in the first key-value pair and the mean value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair.

[0165] Specifically, the sorted first key-value pairs are bucketed, and the average of the historical operating temperatures in the first key-value pairs in each bucket is obtained. By calculating the average value by bucketing, a new set of key-value pairs, namely, the second key-value pairs, is obtained.

[0166] In step S6334, the second key-value pair is input into the second sub-model to train the second sub-model.

[0167] The first predicted temperature in the second key-value pair is the feature value, and the mean value in the second key-value pair is the label.

[0168] Since the second key-value pair is composed of the first predicted value and the average of the historical operating temperatures, the first predicted value is closer to the average of the historical operating temperatures, that is, the predicted value in the second key-value pair is closer to the actual temperature. Therefore, by training the second sub-model with the first predicted temperature in the second key-value pair as the feature value and the average of the second key-value pair as the label, the resulting temperature prediction model can predict the temperature more accurately.

[0169] It can be seen that the temperature predicted by the second sub-model obtained by this implementation is closer to the actual temperature, so that the obtained temperature prediction model can predict the temperature more accurately.

[0170] In a third aspect, the present disclosure provides an information processing device, such as Fig. 9 As shown, including:

[0171] The operation parameter acquisition module 910 is configured to acquire the real-time operation parameters of the target server in the target environment;

[0172] The temperature prediction module 920 is configured to input the real-time operating parameters into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; wherein the temperature prediction model includes a first sub-model and a second sub-model, the first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain a first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0173] The first temperature warning information generating module 930 is configured to generate temperature warning information for the target server based on the target predicted temperature corresponding to the target server when the target predicted temperature corresponding to the target server is greater than a temperature threshold.

[0174] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0175] Optionally, the device further comprises:

[0176] A correlation determination module is configured to determine the correlation between the servers according to the historical operating temperature of the servers and the corresponding target predicted temperature;

[0177] The graph network construction module is configured to construct a correlation graph network based on the server identifications of the servers and the correlation sizes between the servers, wherein the correlation graph network includes multiple nodes, the node identification of each node corresponds to the server identification of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the correlation size between the servers corresponding to the two nodes.

[0178] Optionally, the correlation determination module is specifically configured to execute:

[0179] Determine, according to the historical operating temperature of each server and the corresponding target predicted temperature, an event corresponding to each server, wherein the event is used to describe a change relationship between the historical operating temperature of each server and the corresponding target predicted temperature;

[0180] For each server, count the number of events that occur at the same time with each other service;

[0181] For each server, the correlation between the server and other servers is determined based on the number of identical events occurring between the server and other servers, wherein the correlation is proportional to the number of identical events occurring.

[0182] Optionally, the device further comprises:

[0183] A node acquisition module is configured to execute, when detecting that a first target node exists in the correlation graph network, acquiring a second target node whose correlation with the first target node is greater than a preset correlation, and a target predicted temperature of a server corresponding to the first target node is greater than the temperature threshold;

[0184] A node determination module is configured to determine the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold;

[0185] The second temperature warning information generating module is configured to generate temperature warning information of a server corresponding to the first target node and a server corresponding to the second target node when the number of nodes is greater than a preset number.

[0186] In a fourth aspect, an embodiment of the present disclosure provides a temperature prediction model training device, wherein the temperature prediction model includes a first sub-model and a second sub-model, such as Fig.10 As shown, including:

[0187] The historical data acquisition module 1010 is configured to acquire the historical operating parameters of each server in the target environment and the historical operating temperature of each server;

[0188] The first sub-model training module 1020 is configured to train the first sub-model using the historical operating parameters of each server and the historical operating temperature of each server to obtain a first predicted temperature corresponding to each server;

[0189] The second sub-model training module 1030 is configured to train the second sub-model using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server;

[0190] A loss function value determination module 1040 is configured to determine a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server;

[0191] The temperature prediction model determination module 1050 is configured to determine the trained temperature prediction model when the loss function value is less than a preset loss value.

[0192] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0193] Optionally, the second sub-model training module includes:

[0194] A key-value pair determining unit is configured to execute, for each server, combining a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server into a first key-value pair;

[0195] A training sample determining unit, configured to determine the first key-value pair as a training sample;

[0196] The second sub-model training unit is configured to input the training sample into the second sub-model to train the second sub-model.

[0197] Optionally, the second sub-model training unit is specifically configured to execute:

[0198] Sorting the plurality of first key-value pairs according to the values ​​of the first predicted temperatures in the first key-value pairs to obtain sorted first key-value pairs;

[0199] Divide the sorted first key-value pairs into buckets, and obtain the average of the historical operating temperatures in the first key-value pairs in each bucket;

[0200] For each sorted first key-value pair, the first predicted temperature in the first key-value pair and the average value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair;

[0201] The second key-value pair is input into the second sub-model to train the second sub-model; wherein the first predicted temperature in the second key-value pair is a feature value, and the mean value in the second key-value pair is a label.

[0202] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0203] processor;

[0204] a memory for storing processor-executable instructions;

[0205] Wherein, the processor is configured to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect.

[0206] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0207] Fig.11 1 is a block diagram of an apparatus 1100 for information processing according to an exemplary embodiment. For example, the apparatus 1100 is an electronic device, and specifically can be a mobile phone, a computer, a digital broadcast terminal, a message transceiver device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0208] Reference Fig.11 , the device 1100 may include one or more of the following components: a processing component 1102 , a memory 1104 , a power component 1106 , a multimedia component 11011 , an audio component 1110 , an input / output (I / O) interface 1112 , a sensor component 1114 , and a communication component 1116 .

[0209] The processing component 1102 generally controls the overall operation of the device 1100, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1102 may include one or more modules to facilitate the interaction between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate the interaction between the multimedia component 11011 and the processing component 1102.

[0210] The memory 1104 is configured to store various types of data to support operations on the device 1100. Examples of such data include instructions for any application or method operating on the device 1100, contact data, phone book data, messages, pictures, videos, etc. The memory 1104 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0211] The power supply component 1106 provides power to the various components of the device 1100. The power supply component 1106 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 1100.

[0212] The multimedia component 1108 includes a screen that provides an output interface between the device 1100 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1108 includes a front camera and / or a rear camera. When the device 1100 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0213] The audio component 1110 is configured to output and / or input audio signals. For example, the audio component 1110 includes a microphone (MIC), and when the device 1100 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1104 or sent via the communication component 1116. In some embodiments, the audio component 1110 also includes a speaker for outputting audio signals.

[0214] I / O interface 1112 provides an interface between processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0215] The sensor assembly 1114 includes one or more sensors for providing various aspects of the status assessment of the device 1100. For example, the sensor assembly 1114 can detect the open / closed state of the device 1100, the relative positioning of components, such as the display and keypad of the device 1100, the sensor assembly 1114 can also detect the position change of the device 1100 or a component of the device 1100, the presence or absence of user contact with the device 1100, the orientation or acceleration / deceleration of the device 1100, and the temperature change of the device 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1114 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0216] The communication component 1116 is configured to facilitate wired or wireless communication between the device 1100 and other devices. The device 1100 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 1116 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1116 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0217] In an exemplary embodiment, the device 1100 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned information processing method.

[0218] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1104 including instructions, and the instructions can be executed by a processor 1120 of the device 1100 to perform the above method. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0219] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0220] Fig.12 1 is a block diagram of a device 1200 for information processing or temperature prediction model training according to an exemplary embodiment. For example, the device 1200 may be provided as a server. Fig.12 The apparatus 1200 includes a processing component 1222, which further includes one or more processors, and a memory resource represented by a memory 1232 for storing instructions executable by the processing component 1222, such as an application. The application stored in the memory 1232 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1222 is configured to execute instructions to perform the above-mentioned information processing method or temperature prediction model training method.

[0221] The device 1200 may also include a power supply component 1226 configured to perform power management of the device 1200, a wired or wireless network interface 1250 configured to connect the device 1200 to a network, and an input / output (I / O) interface 1258. The device 1200 may operate based on an operating system stored in the memory 1232, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™, or the like.

[0222] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0223] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the electronic device to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect.

[0224] Since the temperature prediction model is trained through a large amount of historical operating data of each server in the target environment, and includes two layers of models, namely the first sub-model and the second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual operating temperature of the target server, so that the temperature prediction model can more accurately predict the temperature of the target server, so that when the temperature of the target server is high, timely measures can be taken in advance to ensure the safe operation of the target server.

[0225] In a seventh aspect, an embodiment of the present disclosure provides a computer program product, which, when executed on a computer, enables the computer to execute the information processing method described in the first aspect, or the temperature prediction model training method described in the second aspect. Since the temperature prediction model is trained by a large amount of historical operation data of each server in the target environment, and includes two layers of models, namely, a first sub-model and a second sub-model, by training the first sub-model and the second sub-model, the target predicted temperature output by the temperature prediction model can be closer to the actual temperature of the target server, thereby enabling the temperature prediction model to more accurately predict the temperature of the target server, so that when the temperature of the target server is high, measures can be taken in time in advance to ensure the safe operation of the target server.

[0226] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, DSL (Digital Subscriber Line, digital subscriber line)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD (Digital Versatile Disc)), or a semiconductor medium (eg, an SSD (Solid State Disk)), etc.

[0227] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0228] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0229] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information processing method, characterized in that: include: Obtain the real-time operating parameters of the target server in the target environment; The real-time operating parameters are input into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; wherein the temperature prediction model includes a first sub-model and a second sub-model, the first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain a first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server; When the target predicted temperature corresponding to the target server is greater than a temperature threshold, generating temperature warning information for the target server based on the target predicted temperature corresponding to the target server; Wherein, the method comprises: Determining the correlation between the servers according to the historical operating temperatures of the servers and the corresponding target predicted temperatures; Based on the server identification of each server and the size of the correlation between the servers, a correlation graph network is constructed, wherein the correlation graph network includes multiple nodes, the node identification of each node corresponds to the server identification of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the size of the correlation between the servers corresponding to the two nodes.

2. The method according to claim 1, characterized in that The determining the correlation between the servers according to the historical operating temperatures of the servers and the corresponding target predicted temperatures includes: Determine, according to the historical operating temperature of each server and the corresponding target predicted temperature, an event corresponding to each server, wherein the event is used to describe a change relationship between the historical operating temperature of each server and the corresponding target predicted temperature; For each server, count the number of events that occur at the same time as other services. For each server, the correlation between the server and other servers is determined based on the number of identical events occurring between the server and other servers, wherein the correlation is proportional to the number of identical events occurring.

3. The method according to claim 2, characterized in that The method further comprises: When it is detected that the correlation graph network has a first target node, a second target node whose correlation with the first target node is greater than a preset correlation is obtained, and a target predicted temperature of a server corresponding to the first target node is greater than the temperature threshold; Determine the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold; When the number of nodes is greater than a preset number, temperature warning information of the server corresponding to the first target node and the server corresponding to the second target node is generated.

4. A temperature prediction model training method, characterized in that: The temperature prediction model includes a first sub-model and a second sub-model, including: Obtaining historical operating parameters of each server in the target environment and historical operating temperatures of each server; The first sub-model is trained using the historical operating parameters of each server and the historical operating temperature of each server to obtain a first predicted temperature corresponding to each server; The second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server; Determining a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server; When the loss function value is less than a preset loss value, it is determined that a trained temperature prediction model is obtained.

5. The method according to claim 4, characterized in that The training of the second sub-model by using the first predicted temperature of each server and the historical operating temperature of each server includes: For each server, a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server are combined into a first key-value pair; Determining the first key-value pair as a training sample; The training samples are input into the second sub-model to train the second sub-model.

6. The method according to claim 5, characterized in that The step of inputting the training sample into the second sub-model to train the second sub-model includes: Sorting the plurality of first key-value pairs according to the values ​​of the first predicted temperatures in the first key-value pairs to obtain sorted first key-value pairs; Divide the sorted first key-value pairs into buckets, and obtain the average of the historical operating temperatures in the first key-value pairs in each bucket; For each sorted first key-value pair, the first predicted temperature in the first key-value pair and the average value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair; The second key-value pair is input into the second sub-model to train the second sub-model; wherein the first predicted temperature in the second key-value pair is a feature value, and the mean value in the second key-value pair is a label.

7. An information processing device, characterized in that: include: An operation parameter acquisition module is configured to execute and acquire real-time operation parameters of a target server in a target environment; The temperature prediction module is configured to execute inputting the real-time operating parameters into a pre-trained temperature prediction model to obtain a target predicted temperature corresponding to the target server; wherein the temperature prediction model includes a first sub-model and a second sub-model, the first sub-model is trained using the historical operating parameters of each server in the target environment and the historical operating temperature of each server to obtain a first predicted temperature of each server; the second sub-model is trained using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server; A first temperature warning information generating module is configured to generate temperature warning information for the target server based on the target predicted temperature corresponding to the target server when the target predicted temperature corresponding to the target server is greater than a temperature threshold; A correlation determination module is configured to determine the correlation between the servers according to the historical operating temperature of the servers and the corresponding target predicted temperature; The graph network construction module is configured to construct a correlation graph network based on the server identifications of the servers and the correlation sizes between the servers, wherein the correlation graph network includes multiple nodes, the node identification of each node corresponds to the server identification of a server, and the weight corresponding to the edge connecting any two nodes in the correlation graph network is the correlation size between the servers corresponding to the two nodes.

8. The device according to claim 7, characterized in that The correlation determination module is specifically configured to execute: Determine, according to the historical operating temperature of each server and the corresponding target predicted temperature, an event corresponding to each server, wherein the event is used to describe a change relationship between the historical operating temperature of each server and the corresponding target predicted temperature; For each server, count the number of events that occur at the same time as other services. For each server, the correlation between the server and other servers is determined based on the number of identical events occurring between the server and other servers, wherein the correlation is proportional to the number of identical events occurring.

9. The device according to claim 8, characterized in that The device also includes: A node acquisition module is configured to execute, when detecting that a first target node exists in the correlation graph network, acquiring a second target node whose correlation with the first target node is greater than a preset correlation, and a target predicted temperature of a server corresponding to the first target node is greater than the temperature threshold; A node determination module is configured to determine the number of nodes in the second target node whose target predicted temperature of the corresponding server is greater than the temperature threshold; The second temperature warning information generating module is configured to generate temperature warning information of a server corresponding to the first target node and a server corresponding to the second target node when the number of nodes is greater than a preset number.

10. A temperature prediction model training device, characterized in that: The temperature prediction model includes a first sub-model and a second sub-model, including: A historical data acquisition module is configured to acquire historical operating parameters of each server in the target environment and historical operating temperatures of each server; A first sub-model training module is configured to train the first sub-model using the historical operating parameters of each server and the historical operating temperature of each server to obtain a first predicted temperature corresponding to each server; A second sub-model training module is configured to train the second sub-model using the first predicted temperature of each server and the historical operating temperature of each server to obtain a target predicted temperature corresponding to each server; A loss function value determination module, configured to determine a loss function value of a temperature prediction model based on a target predicted temperature corresponding to each server and a historical operating temperature of each server; The temperature prediction model determination module is configured to determine the trained temperature prediction model when the loss function value is less than a preset loss value.

11. The device according to claim 10, characterized in that The second sub-model training module includes: A key-value pair determining unit is configured to execute, for each server, combining a first predicted temperature corresponding to the server and a historical operating temperature corresponding to the server into a first key-value pair; A training sample determining unit, configured to determine the first key-value pair as a training sample; The second sub-model training unit is configured to input the training sample into the second sub-model to train the second sub-model.

12. The device according to claim 11, characterized in that The second sub-model training unit is specifically configured to execute: Sorting the plurality of first key-value pairs according to the values ​​of the first predicted temperatures in the first key-value pairs to obtain sorted first key-value pairs; Divide the sorted first key-value pairs into buckets, and obtain the average of the historical operating temperatures in the first key-value pairs in each bucket; For each sorted first key-value pair, the first predicted temperature in the first key-value pair and the average value corresponding to the bucket where the first key-value pair is located are combined into a second key-value pair; The second key-value pair is input into the second sub-model to train the second sub-model; wherein the first predicted temperature in the second key-value pair is a feature value, and the mean value in the second key-value pair is a label.

13. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the information processing method described in any one of claims 1-3, or the temperature prediction model training method described in any one of claims 4 to 6.

14. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by the processor of the mobile terminal, the electronic device is enabled to execute the information processing method described in any one of claims 1-3, or the temperature prediction model training method described in any one of claims 4 to 6.

15. A computer program product, characterized in that When it runs on a computer, it enables the computer to execute the information processing method described in any one of claims 1 to 3, or the temperature prediction model training method described in any one of claims 4 to 6.

Images