CN111738765A

CN111738765A - Data processing method, device, equipment and storage medium

Info

Publication number: CN111738765A
Application number: CN202010579634.2A
Authority: CN
Inventors: 游悦
Original assignee: JD Digital Technology Holdings Co Ltd
Current assignee: JD Digital Technology Holdings Co Ltd
Priority date: 2020-06-23
Filing date: 2020-06-23
Publication date: 2020-10-02

Abstract

An embodiment of the application provides a data processing method, a device, equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps that values of first parameters under a plurality of time units included in a first period are obtained based on a user request aiming at a first object and sent by at least one client side in the first period, wherein the user request can influence the values of the first parameters of the first object; and predicting the predicted values of the first parameter in a plurality of time units in a second period according to the historical values of the first parameter in the plurality of time units, wherein the second period is the next period of the first period. According to the embodiment of the application, by predicting the predicted values of the parameters of the object in a plurality of time units in the next period, whether the parameters have problems or not can be determined in time based on the predicted values of the parameters, and the maintenance reliability of the object is improved.

Description

Data processing method, device, equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a data processing method, a data processing device, data processing equipment and a storage medium.

Background

In a maintenance scenario of an object, multiple parameters affecting the object need to be monitored, and if a problem occurs in a certain parameter, the object may be degraded.

Currently, in an advertisement maintenance scenario, for a parameter (such as an advertisement click rate) affecting an advertisement operation, it is generally determined whether a problem occurs in the parameter during a historical time period according to a value of the parameter during the historical time period. In the process of implementing the present application, the inventor finds that at least the following problems exist in the prior art: it is not possible to determine in time whether the parameter is problematic.

Disclosure of Invention

The embodiment of the application provides a data processing method, a data processing device, data processing equipment and a storage medium, which are used for solving the problem that whether parameters can be determined in time or not.

In a first aspect, an embodiment of the present application provides a data processing method, applied to a server, including: the method comprises the steps that values of a first parameter under a plurality of time units included in a first period are obtained based on a user request aiming at a first object and received in the first period, wherein the user request can influence the values of the first parameter of the first object; and predicting the predicted values of the first parameter in a plurality of time units in a second period according to the historical values of the first parameter in the plurality of time units, wherein the second period is the next period of the first period. Optionally, the first object is a finance-related object.

According to the scheme, the predicted values of the first parameters under the multiple time units in the second period are predicted according to the historical values of the first parameters under the multiple time units in the first period, the second period is the next period of the first period, whether the first parameters have problems in the next period can be predicted based on the predicted values of the first parameters, whether the parameters have problems can be determined timely, and the maintenance reliability of the object is improved.

In one possible embodiment, the predicting, according to the historical values of the first parameter in the plurality of time units, the predicted value of the first parameter in the plurality of time units included in the second period includes: obtaining the predicted value by using a neural network model by using the historical value; the neural network model is trained based on a plurality of training samples, and the training samples comprise numerical values of the first parameter in a plurality of time units respectively included in two adjacent historical periods.

The embodiment has the following advantages or beneficial effects: the obtained predicted value of the first parameter is more accurate.

In one possible embodiment, the method further comprises: analyzing the predicted value based on a preset judgment condition of the first parameter to obtain first abnormal information of the first parameter in the second period; and sending the first abnormal information to the terminal equipment.

The embodiment has the following advantages or beneficial effects: in the embodiment, when the first parameter is abnormal in the second period, the server sends the abnormal information of the first parameter in the second period to the first terminal device, so that the user can timely know that the first parameter is abnormal in the second period, and at the moment, the user can take corresponding measures to prevent the first parameter from being abnormal in the second period, thereby improving the maintenance reliability of the first object.

In a possible implementation manner, after obtaining the first abnormal information of the first parameter in the second period, the method further includes: determining a target attribute causing the first parameter exception in the second period according to various attributes of a user corresponding to the user request; and sending the target attribute to the terminal equipment.

The embodiment has the following advantages or beneficial effects: the server analyzes the reason causing the first parameter abnormity in the second period and sends the reason to the first terminal equipment, and the reason can assist the user to take corresponding measures to prevent the first parameter from abnormity in the second period, so that the object maintenance reliability is further improved.

In a possible implementation manner, the determining the target class attribute causing the first parameter exception in the second period includes: for each attribute, acquiring an influence coefficient of the attribute on the first parameter; and determining the target attribute from the plurality of attributes according to the influence coefficients of various attributes on the first parameter.

The embodiment has the following advantages or beneficial effects: according to the influence coefficients of various attributes on the first parameter, the target attribute is determined from the multiple attributes, and the accuracy of the determined reason causing the abnormality of the first parameter in the second period can be improved.

In a possible embodiment, the obtaining the influence coefficient of the attribute on the first parameter includes: acquiring at least one category corresponding to the attribute; and acquiring the influence coefficient of the attribute on the first parameter according to the total number of the users and the number of the users in each category.

The embodiment has the following advantages or beneficial effects: a specific implementation of obtaining an influence coefficient of an attribute on a first parameter is given.

In one possible embodiment, before predicting the predicted value of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units, the method further includes: receiving a prediction request from a terminal device, wherein the prediction request is used for requesting prediction of a prediction value of the first parameter in a plurality of time units included in the second period; and sending the predicted values of the first parameter under a plurality of time units included in the second period to the terminal equipment.

The embodiment has the following advantages or beneficial effects: in the embodiment, after the request triggered by the user is received, the numerical value of the first parameter in the second period is predicted, so that the power consumption of the server can be saved.

In a possible implementation, the first parameter is a parameter in a preset parameter set.

The embodiment has the following advantages or beneficial effects: the parameters in the preset parameter set are predicted in the next period, so that the power consumption of the server can be saved.

In one possible embodiment, the method further comprises: receiving an analysis request from a terminal device, wherein the analysis request is used for analyzing a value of a second parameter in a first historical time period, and the second parameter does not belong to the preset parameter set; responding to the analysis request, analyzing the value of the second parameter in the first historical time period to obtain second abnormal information of the second parameter in the first historical time period; and sending the second abnormal information to the terminal equipment.

The embodiment has the following advantages or beneficial effects: for the parameters which are not in the preset parameter set, whether the parameters are normal in the historical time period is analyzed after the analysis request triggered by the user is received, and the power consumption of the server can be saved.

In one possible embodiment, the method further comprises: obtaining a predicted change curve of the first parameter in the second period according to the predicted value; and sending the predicted change curve to the terminal equipment.

The embodiment has the following advantages or beneficial effects: the user can be enabled to more intuitively know the characteristics of the first parameter in the second period.

In one possible embodiment, the method further comprises: and sending the prediction value to the terminal equipment.

The embodiment has the following advantages or beneficial effects: the user may be made aware of the predicted value of the first parameter during the second period.

In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a server, and includes: acquiring numerical values of the first parameter in a plurality of time units included in a first period; according to values of the first parameter in a plurality of time units included in a first period, obtaining predicted values of the first parameter in a plurality of time units included in a second period, wherein the second period is the next period of the first period.

In a third aspect, an embodiment of the present application provides a data processing apparatus, including: the processing module is used for acquiring numerical values of a first parameter under a plurality of time units included in a first period based on a user request aiming at a first object and received by at least one client in the first period, wherein the user request can influence the numerical values of the first parameter of the first object; the processing module is further configured to predict, according to the historical values of the first parameter in the multiple time units, a predicted value of the first parameter in the multiple time units included in a second period, where the second period is a next period of the first period.

In one possible implementation, the processing module is specifically configured to: obtaining the predicted value by using a neural network model by using the historical value; the neural network model is trained based on a plurality of training samples, and the training samples comprise numerical values of the first parameter in a plurality of time units respectively included in two adjacent historical periods.

In a possible implementation manner, the processing module is further configured to analyze the predicted value based on a preset determination condition of the first parameter, so as to obtain first abnormal information of the first parameter in the second period; the receiving and sending module is used for sending the first abnormal information to the terminal equipment.

In one possible implementation manner, after the processing module obtains the first exception information of the first parameter in the second period: the processing module is further configured to determine, according to multiple attributes of the user corresponding to the user request, a target attribute that causes the first parameter to be abnormal in the second period; the transceiver module is further configured to send the target attribute to a terminal device.

In one possible implementation, the processing module is specifically configured to: for each attribute, acquiring an influence coefficient of the attribute on the first parameter; and determining the target attribute from the plurality of attributes according to the influence coefficients of various attributes on the first parameter.

In one possible implementation, the processing module is specifically configured to: acquiring at least one category corresponding to the attribute; and acquiring the influence coefficient of the attribute on the first parameter according to the total number of the users and the number of the users in each category.

In one possible implementation, before the processing module predicts the predicted value of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units: the processing module is further configured to receive a prediction request from a terminal device, where the prediction request is used to request prediction of predicted values of the first parameter in a plurality of time units included in the second period; the transceiver module is further configured to send the predicted values of the first parameter in the plurality of time units included in the second period to the terminal device.

In one possible embodiment, the system further comprises a transceiver module; the transceiver module is configured to receive an analysis request from a terminal device, where the analysis request is used to analyze a value of a second parameter in a first historical time period, and the second parameter does not belong to the preset parameter set; the processing module is further configured to respond to the analysis request, and analyze a value of the second parameter in the first historical time period to obtain second abnormal information of the second parameter in the first historical time period; the transceiver module is further configured to send the second abnormal information to a terminal device.

In one possible embodiment, the system further comprises a transceiver module; the processing module is further configured to obtain a predicted change curve of the first parameter in the second period according to the predicted value; and the transceiver module is used for transmitting the predicted change curve to the terminal equipment.

In one possible embodiment, the first object is a finance-related object.

In a fourth aspect, an embodiment of the present application provides a data processing apparatus, including: the processing module is used for acquiring numerical values of the first parameter in a plurality of time units included in a first period; the processing module is further configured to obtain predicted values of the first parameter in multiple time units included in a second period according to the values of the first parameter in multiple time units included in the first period, where the second period is a next period of the first period.

In a fifth aspect, an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect and any one of the possible implementations of the first aspect or to perform the method of the second aspect.

In a sixth aspect, embodiments of the present application provide a computer-readable storage medium, where computer-executable instructions are stored, and when executed by a processor, are configured to implement the method as described in the first aspect and any possible implementation manner of the first aspect, or perform the method as described in the second aspect.

According to the technical means, the server obtains the values of the first parameters under the multiple time units included in the first period based on the user request aiming at the first object and sent by the at least one client side in the first period, and then predicts the predicted values of the first parameters under the multiple time units included in the second period (the second period is the next period of the first period) according to the historical values of the first parameters under the multiple time units included in the first period, so that whether the first parameters can be predicted in the next period based on the predicted values of the first parameters can be realized, the technical problem that whether the parameters can be determined to be problematic in the next period can be solved, whether the parameters can be determined to be problematic in time can be realized, and the effect of improving the object maintenance reliability can be achieved.

Drawings

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 disclosure.

FIG. 1 is a diagram of a system architecture provided by an embodiment of the present application;

fig. 2 is a first flowchart of a data processing method according to an embodiment of the present application;

fig. 3 is a second flowchart of a data processing method according to an embodiment of the present application;

fig. 4 is a flowchart of a data processing method according to an embodiment of the present application;

FIG. 5 is a flowchart IV of a data processing method according to an embodiment of the present application

Fig. 6 is a fifth flowchart of a data processing method according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a data processing apparatus according to an embodiment of the present application;

fig. 8 is a schematic view of an electronic device according to an embodiment of the present application.

With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In some object maintenance scenarios, such as advertisement maintenance, financial system maintenance, etc., multiple parameters affecting the object need to be monitored, and if a problem occurs in a certain parameter, the object may be degraded. For example, in a scenario of financial system maintenance, the following parameters may be monitored: the total number of persons who keep each day, total amount of money actively traded each day, total number of persons actively traded each day of each financing product under the financial system; and the respective active redemption amount, the active redemption number, the number of newly-increased account opening users each day, the number of active users each day, the number of thousands of yuan of account keeping each day, and the like of each financing product. Wherein the active user may be a user logged into an application for the financial system. The number of people is kept in thousands yuan every day: the number of thousands of dollar holdings per day in a week is an average of the number of thousands of dollar holdings per week, which means that the value of the financial product purchased is greater than or equal to 1000 dollars.

Currently, for a parameter affecting an advertisement operation, it is generally determined whether a problem occurs in the parameter during a historical time period according to a historical value of the parameter during the historical time period. In the process of implementing the present application, the inventor finds that at least the following problems exist in the prior art: it is determined whether the parameter has a problem in a history time period, whether the parameter has a problem cannot be determined in time, and the reliability of the maintenance of the object is not high.

In order to solve the above-mentioned technical problems, the inventors have found that if a future value of a parameter can be predicted, it is possible to determine in time whether the parameter is problematic, thereby improving the reliability of maintenance of an object.

The system architecture to which the present application relates is explained below.

Fig. 1 is a system architecture diagram provided in an embodiment of the present application. Referring to fig. 1, the system architecture includes: client, server, maintenance end equipment.

The client is a terminal device capable of triggering a request of a user for a certain object, for example, if the object is a financial product, the client is a terminal device installed with an application capable of processing the financial product; for another example, if the object is an advertisement, the client is a terminal device capable of receiving and displaying the advertisement to the user.

After receiving a request for a certain object input by a user, the client sends the request to the server. In addition to responding to the request, if the request can affect the value of a certain parameter of the object, the server will also update the value of the first parameter in the time unit corresponding to the user request. The time unit corresponding to the user request is the time unit to which the occurrence time of the user request belongs. It is understood that the server may count the value of the parameter for a plurality of time units included in the first cycle based on the request capable of affecting the parameter received by the first cycle, where the time units may be any time units of one day, one week, two weeks, one month, one year, and the like. Next, the server may predict a predicted value of the parameter for a plurality of time units included in a next cycle of the first cycle based on the historical values of the parameter for the plurality of time units included in the first cycle, and the first cycle may be a cycle that has just passed. Therefore, whether the parameter has a problem or not can be determined in time based on the predicted values of the parameter in a plurality of time units included in the next period, and the maintenance reliability of the object is improved.

The specific implementation of the prediction of whether the parameter will have a problem in the next period is as follows: in one mode, after obtaining the predicted values of the parameter in the time units included in the next period, the server may analyze the predicted values, and if the analysis result is that the abnormal information of the parameter in the next period is obtained, the server may send the abnormal information to the maintenance-side device. The maintenance end device displays the abnormal information, and a user can timely know that the parameter is abnormal in the next period, so that corresponding measures can be timely taken to prevent the parameter from being abnormal in the next period, and the maintenance reliability of the object is greatly improved. In addition, in this way, the server may also send the predicted value to the maintenance-side device. In another mode, after obtaining the predicted values of the parameter in the plurality of time units included in the next period, the server sends the predicted values to the maintenance-side device, the maintenance-side device displays the predicted values, and the user can analyze whether the parameter has a problem in the next period based on the predicted values.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Fig. 2 is a first flowchart of a data processing method provided in an embodiment of the present application, and referring to fig. 2, the method of the present embodiment includes:

step S201, the server obtains values of the first parameter in multiple time units included in the first period based on a user request for the first object sent by at least one client received in the first period, where the user request can affect the values of the first parameter of the first object.

The user request in this embodiment is a user request that can affect the value of the first parameter of the first object. After receiving the user request aiming at the first object, the client sends the user request to the server, and the server receives the user request.

For example, if the first object is a first financial product and the user request is to redeem the first financial product with the first value, the user request may affect the number of active redeeming persons, the number of active users, the number of active trading persons, etc. of the first financial product, that is, the first parameter at this time may be: the number of active redeeming people or the number of active users or the number of active trading people.

For another example, the first object is a first financial system, the first financial system includes a plurality of financial products, and the user request is to redeem all of the financial products purchased by the user, and the user request may affect the total number of persons held, total amount of active transactions, total number of active transactions, and the like of the first financial system, that is, the first parameter at this time may be: total number of persons who hold the money or total amount of active transaction or total number of persons who actively transact the money.

For another example, the first object is a first financial system, the first financial system includes a plurality of financial products, the plurality of financial products includes a first financial product, and the user request is a first financial product redeemed for a certain value, so the user request may affect the total active transaction amount of the first financial system, the number of active redeeming persons of the first financial product under the first financial system, the number of active users of the first financial product, the number of active transaction persons of the first financial product, and the like, that is, the first parameter at this time may be: the total amount of the active transaction or the total number of the active transaction or the number of active redeeming persons of the first financial product or the number of active users of the first financial product or the number of active transactions of the first financial product.

And the server responds to the user request after receiving the user request. In addition, since the user requests the value of the first parameter that can affect the first object, in the case where the server counts the values of the first parameter in units of time units, the server also updates the value of the first parameter in the time unit corresponding to the user request. The time unit corresponding to the user request is the time unit to which the occurrence time of the user request belongs. It is to be understood that the server may obtain the values of the first parameter at a plurality of time units included in the first period based on a user request for the first object sent by at least one client received within the first period. The time unit may be any time unit such as one day, one week, two weeks, one month, one year, and the like, and is not limited in this embodiment. The time units corresponding to different parameters may be different or the same.

One cycle in this embodiment includes N time units: the first cycle may be N consecutive time units including the current day, and the N consecutive time units include a day previous to the current day; alternatively, the first period may include N consecutive time units before the current day.

Illustratively, the first object is a first financial product, the user request is to redeem a value of the first financial product, the time unit is one day, the first period is the first 7 days including the current day, and the first parameter is an active redemption number of people, then the server may obtain a value of the active redemption number of people per day on the last 7 days including the current day based on the user request to redeem the financial product received on the first 7 days including the current day.

Step S202, the server predicts the predicted values of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units included in the first period. The second cycle is the next cycle of the first cycle.

Illustratively, the first object is a first financial product, the user request is to redeem a value of the first financial product, the first parameter is an active redemption number, the time unit is one day, the first period includes the first 7 days of the current day, and the server may predict a value of the active redemption number for each day 7 days after the current day based on a value of the active redemption number for each day of the consecutive 7 days including the current day.

In one mode: the server predicts the predicted values of the first parameter under the plurality of time units included in the second period according to the historical values of the first parameter under the plurality of time units included in the first period, and the method comprises the following steps: acquiring predicted values of the first parameter under a plurality of time units included in the second period by using historical values of the first parameter under a plurality of time units included in the first period and a neural network model; the neural network model is obtained by training based on a plurality of training samples, wherein the training samples comprise numerical values of the first parameter of the first object in a plurality of time units respectively included in two adjacent historical periods. In this manner, the first period and the second period include the same number of time units, and the two adjacent history periods in the training sample include the same number of time units as the first period.

For any first training sample, two adjacent history cycles corresponding to the first training sample are a history cycle 1 and a history cycle 2, and the history cycle 2 is the next cycle of the history cycle 1. In the training process, the input of the neural network is obtained according to the values of the first parameter under a plurality of time units included in the historical period 1, and the expected output of the neural network is obtained according to the values of the first parameter under a plurality of time units included in the historical period 2.

Optionally, the neural network model may be a Long Short Term memory neural network (LSTM) model, and the algorithm used in the training process is an LSTM neural network algorithm. At this time, the input obtained according to the numerical values of the first parameter in the plurality of time units included in the history cycle 1 is a plurality of sequences, each sequence is a vector corresponding to the numerical value of the first parameter in one time unit included in the history cycle 1, and the plurality of sequences are input to the neural network according to the sequence of the corresponding time units. The input obtained according to the historical numerical values of the first parameter in the plurality of time units included in the historical period 2 is also a plurality of sequences, and the plurality of sequences are arranged according to the sequence of the corresponding time units to be used as the expected output of the neural network.

The LSTM neural network algorithm provided in the embodiments of the present application is explained below.

X_t-1For input of a certain neuron S at time t-1, h_t-1When the input is X_t-1Output of temporal neuron S, C_t-1Is the state of neuron S corresponding to time t-1, X_tFor input of neuron S at time t, h_tWhen the input is X_tOutput of temporal neuron S, C_tIs the state of neuron S corresponding to time t, X_t+1Is the input of neuron S at time t +1, h_t+1When the input is X_t+1Output of temporal neuron S, C_t+1The state of the corresponding neuron S at time t + 1.

That is, at time t, neuron S has three inputs: c_t-1，X_t，h_t-1。

Where a neuron S has different inputs and outputs at different times. For time t, X_tIs calculated according to the output of each neuron in the upper layer and the connection weight between each neuron in the upper layer and the neuron S, h_t-1Also referred to as the output of the neuron S, C, at the previous moment_t-1Also referred to as the state of neuron S at the previous time, all that needs to be done now is to compute the input X of neuron S at time t_tRear output h_t. Can be calculated by formula one to formula six:

f_t＝σ(W_f·[h_t-1,x_t]+b_f) A first formula;

i_t＝σ(W_i·[h_t-1,x_t]+b_i) A second formula;

O_t＝σ(W_O·[h_t-1,x_t]+b_O) A formula V;

h_t＝O_t·tanh(C_t) A formula six;

wherein f is_tTo forget the door, W_fWeight matrix for forgetting gate, b_fBias term for forgetting gate, σ is sigmoid function, i_tIs an input gate, W_iAs a weight matrix of the input gates, b_iIn order to input the offset term of the gate,

for describing the state of the current input, C_tNew state of neuron corresponding to time t, O_tIs an output gate, W_OAs a weight matrix of output gates, b_OTo output the offset term of the gate, h_tThe final output corresponding to the neuron S at the time t is obtained.

Through the above process, the LSTM neural network combines the current and long-term memory to form a new cell state C_t. Because of the control of the forgetting gate, the LSTM neural network can store information long before, and because of the control of the input gate, the LSTM neural network can prevent the current irrelevant content from entering the memory; the output gate controls the effect of long-term memory on the current output.

In another mode: the server predicts the predicted values of the first parameter under the plurality of time units included in the second period according to the historical values of the first parameter under the plurality of time units included in the first period, and the method comprises the following steps: and obtaining the predicted values of the first parameter in a plurality of time units included in the second period by using the historical values of the first parameter in a plurality of time units included in the first period and a time sequence algorithm. In this manner, the first period and the second period may be different or the same.

Optionally, the first parameter in this embodiment is a parameter in a preset parameter set. The preset parameter set may be a parameter having a larger influence on the first object, or a core parameter of the first object. That is to say, when the first parameter is a parameter in the preset parameter set, the process of predicting the predicted value of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units included in the first period may be automatically triggered, and the user does not need to trigger the prediction process, thereby improving the prediction efficiency.

When the first parameter is not a parameter in the preset parameter set, it indicates that the first parameter has no significant influence on the first object, and at this time, before the server predicts the predicted value of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units included in the first period, the method of this embodiment may further include: receiving a prediction request from the first terminal device, the prediction request requesting prediction of predicted values of the first parameter in a plurality of time units included in the second period, and sending the predicted values of the first parameter in the plurality of time units included in the second period to the terminal device. The first terminal device may be the above-mentioned maintenance terminal device. That is, for a parameter that has little influence on the first object, the predicted value of the parameter in a plurality of time units included in the next cycle may be predicted after receiving a prediction request triggered by a user, so that power consumption of the server may be saved.

In the embodiment, the predicted values of the first parameters in the multiple time units included in the second period are predicted according to the historical values of the first parameters in the multiple time units included in the first period, and the second period is the next period of the first period, so that whether the first parameters have problems in the next period can be timely known based on the predicted values of the first parameters, and the maintenance reliability of the object is improved.

A data processing method corresponding to the server after obtaining the predicted values of the first parameter in the plurality of time units included in the second period is described below with several specific embodiments.

When the first parameter is normal in the second period, it corresponds to the embodiment shown in fig. 3. Fig. 3 is a second flowchart of a data processing method provided in the embodiment of the present application, and referring to fig. 3, the method of the embodiment includes:

step S301, the server analyzes the predicted values of the first parameter in the multiple time units included in the second period based on the first preset judgment condition of the first parameter, and obtains first abnormal information of the first parameter in the second period.

After obtaining the predicted values of the first parameter in the plurality of time units included in the second period, the server analyzes the predicted values of the first parameter based on a first preset judgment condition of the first parameter. The first preset judgment condition includes but is not limited to:

(1) and if the overall change trend of the first parameter in the second period is an ascending trend, judging that the first parameter in the second period is abnormal, otherwise, judging that the first parameter in the second period is normal.

The larger the first parameter corresponding to the first preset judgment condition is, the more favorable the scene of the first object is. At this time, the first abnormal information may indicate that the first parameter is abnormal in the second period and the abnormal condition is an overall trend of change.

(2) And if the overall change trend of the first parameter in the second period is a descending trend, judging that the first parameter in the second period is abnormal, otherwise, judging that the first parameter in the second period is normal.

The smaller the first parameter corresponding to the first preset judgment condition is, the more favorable the scene of the first object is. At this time, the first abnormal information may indicate that the first parameter is abnormal in the second period and the abnormal condition is a general trend of change decreasing.

(3) And if the value of the first parameter in at least h time units in the second period is less than or equal to a first preset value, judging that the first parameter in the second period is abnormal, otherwise, judging that the first parameter in the second period is normal. H is a positive integer smaller than H, H is the number of time units included in the second period, and H is equal to N in the case that the first period and the second period are the same. Optionally, h is greater than or equal to 2. The preset value may be an average value of values of the first parameter in a plurality of time units included in L consecutive periods before the second period, and L may be an integer greater than or equal to 1.

The larger the first parameter corresponding to the first preset judgment condition is, the more favorable the scene of the first object is.

At this time, the first abnormal information may indicate that the first parameter is abnormal in the second period and the abnormal condition is h in the second period₁The value of the first parameter in each time unit is less than a preset value and can also indicate h₁A time unit. h is₁Is an integer greater than or equal to H and less than or equal to H.

(4) And judging that the first parameter in the second period is abnormal if the value of the first parameter under h time units in the second period is greater than or equal to a first preset value, or judging that the first parameter in the second period is normal if the value of the first parameter is not greater than or equal to the first preset value. The preset value may be an average value of values of the first parameter in a plurality of time units included in L consecutive periods before the second period.

The smaller the first parameter corresponding to the first preset judgment condition is, the more favorable the scene of the first object is.

At this time, the first abnormal information may indicate that the first parameter is abnormal in the second period and the abnormal condition is h in the second period₂The value of the first parameter in each time unit is less than a preset value and can also indicate h₂A time unit. h is₂Is an integer greater than or equal to H and less than or equal to H.

It should be understood that the first preset determining condition is only an example, and may also be other types of first preset determining conditions, and details are not described here.

Optionally, the server may further obtain a variation trend curve of the first parameter in the second period according to the predicted values of the first parameter in the plurality of time units included in the second period.

Step S302, the server sends first abnormal information to the first terminal device.

And after obtaining the first abnormal information, the server sends the first abnormal information to the first terminal equipment.

Optionally, the server may further send, to the first terminal device, the predicted values of the first parameter for a plurality of time units included in the second period.

Optionally, in a case that the server acquires a change trend curve of the first parameter in the second period, the server may further send the change trend curve of the first parameter in the second period to the first terminal device.

Step S303, the first terminal device displays an abnormal condition of the first parameter in the second period based on the first abnormal information.

Optionally, if the first terminal device receives the predicted values of the first parameter in the plurality of time units included in the second period, the predicted values of the first parameter in the plurality of time units included in the second period may also be displayed. At this time, when the change trend curve of the first parameter in the second period sent by the server is not received, the method may further include obtaining the change trend curve of the first parameter in the second period according to the predicted values of the first parameter in the plurality of time units included in the second period, and displaying the change trend curve.

Optionally, in this embodiment, the displaying, by the first terminal device, the predicted values of the first parameter in the plurality of time units included in the second period includes: the first terminal device displays the predicted values of the first parameter in a plurality of time units included in the second period in the first display state. The first display state may include at least one of: displaying in a preset color, displaying in a preset font, displaying in a preset size, displaying the background as a preset background, and displaying in a preset font format.

Optionally, when the first preset determination condition is (3) or (4) above, the method may further include: the first terminal device displays h included in the second period in the first display state₁Or h₂The predicted values of the first parameter in the first time unit and the predicted values of the first parameter in the other time units of the second period are displayed in a second display state.

In this embodiment, when the first parameter is abnormal in the second period, the server sends the abnormal information of the first parameter in the second period to the first terminal device, so that the user can timely know that the first parameter is abnormal in the second period, and at this time, the user can take corresponding measures to prevent the first parameter from being abnormal in the second period, thereby improving the maintenance reliability of the first object.

It can be understood that, when the server analyzes the predicted values of the first parameter in the plurality of time units included in the second period based on the first preset judgment condition of the first parameter and determines that the first parameter is normal in the second period, the server may not send any information to the first terminal device, or the server sends information that the first parameter is normal in the second period and/or the predicted values of the first parameter in the plurality of time units included in the second period to the terminal device.

In addition, the server may not analyze the predicted values of the first parameter in the plurality of time units included in the second period, obtain the predicted values of the first parameter in the plurality of time units included in the second period, send the obtained predicted values to the first terminal device, so that the first terminal device displays the predicted values of the first parameter in the plurality of time units included in the second period, and the user may determine whether the first parameter is normal in the second period according to the predicted values of the first parameter in the plurality of time units included in the second period.

After the server analyzes and analyzes the predicted values of the first parameter in the multiple time units included in the second period based on the first preset judgment condition of the first parameter to obtain the first abnormal information, the server can also analyze the reason causing the abnormality of the first parameter in the second period so as to assist the user to take corresponding measures to prevent the abnormality of the first parameter in the second period, and further improve the object maintenance reliability. The data processing method in this case will be described below with specific examples. Fig. 4 is a flow chart of a data processing method provided in the embodiment of the present application, and referring to fig. 4, the method of the embodiment includes:

step S401, the server determines, according to the multiple attributes of the user corresponding to the user request received in the first period, a target attribute causing the first parameter exception in the second period.

The meaning of the user request in this embodiment is the same as that of the user request in the above embodiments, that is, the user request of the first parameter capable of affecting the first object.

The user corresponding to the user request refers to the user who initiates the user request. Each user initiating a user request has a variety of attributes. Where the first object is a first financial system, the attributes of the user include, but are not limited to, at least one of: age, gender, region, mobile phone model, academic history, purchasing power of a user on a preset application (wherein the preset application is an application associated with the first financial system but not the first financial system application itself), loyalty of the user to the preset application, value of the user to the preset application, whether a itemization function (p is an integer greater than or equal to 2, such as 30) is used when the user purchases an article on the preset application in the last p days, an itemization amount of the itemization order in the last p days, whether a financial product of the first financial system is purchased, a total value of the financial product of the first financial system is purchased, whether an active transaction is performed in the first period, a total value of the active transaction performed in the first period, and whether the total value of the financial product of the first financial system owned in the first period exceeds a thousand yuan.

In one approach, the server determines the target attribute that caused the first parameter exception during the second period, including a 1-a 2:

a1, for each attribute, the server obtains the influence coefficient of the attribute on the first parameter.

The server may use a Gini coefficient (GINI) for the attribute as an influence coefficient of the attribute on the first parameter. At this time, the server obtains an influence coefficient of the attribute on the first parameter, including: the server obtains at least one category corresponding to the attribute, and obtains the influence coefficient of the attribute on the first parameter according to the total number of users and the number of users in each category. The Gini coefficient is a similar way to information entropy for feature selection, and can be used to measure the uncertainty of information according to the purity of data.

The server obtains the influence coefficient of the attribute on the first parameter according to the total number of the users and the number of the users in each category, and the method comprises the following steps: and for each category corresponding to the attribute, acquiring a square value of a ratio of the number of users belonging to the category to the total number of the users, and taking a difference value between 1 and the sum of the square values as an influence coefficient of the attribute on the first parameter.

The method for obtaining the influence coefficient gini (p) of the attribute on the first parameter can be expressed as the following formula:

wherein K represents the total number of categories corresponding to the attribute, | C_k| represents the number of users belonging to the kth category, | D | represents the total number of users to which the user requests.

Illustratively, an attribute for gender includes both male and female. The total number of the users corresponding to the user request is 100, the number of the male users is 40, and the number of the male users is 60, then

a2, determining the first target attribute according to the influence coefficient of various attributes on the first parameter.

The first target attribute is a main cause for causing the first parameter abnormality in the second period.

After the attributes are sorted according to the order of the influence coefficients from large to small, the T attributes which are sorted at the top T are all used as first target attributes. Where T is an integer greater than or equal to 1, for example, T ═ 5.

Step S402, the server sends the first target attribute to the first terminal device.

Step S403, the first terminal device displays the first target attribute.

In this embodiment, the server analyzes the reason causing the abnormality of the first parameter in the second period and sends the reason to the first terminal device, so that the user can timely know the reason causing the abnormality of the first parameter in the second period, and the user is assisted to take corresponding measures to prevent the abnormality of the first parameter in the second period, thereby further improving the object maintenance reliability.

As described above, in order to save the power consumption of the server, the parameters in the preset parameter set may be automatically subjected to values in a plurality of time units in the next period. Then, for other parameters that can affect the first object, after receiving the analysis request from the user, it is sufficient to analyze whether the analysis is normal within the historical time period. The data processing method in this case will be described below with specific examples. Fig. 5 is a fourth flowchart of a data processing method provided in the embodiment of the present application, and referring to fig. 5, the method of the embodiment includes:

step S501, the first terminal device sends an analysis request to the server, wherein the analysis request is used for requesting to analyze the value of the second parameter in the first historical time period, and the second parameter is not a parameter in the preset parameter set.

Wherein, the first historical time period can be any day, week, month, year, etc.

Step S502, the server responds to the analysis request, and analyzes the value of the second parameter in the first historical time period based on the second preset judgment condition of the second parameter to obtain second abnormal information of the second parameter in the first historical time period.

The second preset judgment condition includes but is not limited to:

(1) and judging that the second parameter is abnormal in the first historical time period when the overall change trend is rising, and otherwise, judging that the second parameter is normal in the first historical time period.

The larger the second parameter corresponding to the second preset judgment condition is, the more favorable the scene of the first object is. At this time, the second abnormality information may indicate that the second parameter is abnormal within the first history time period and that the abnormal situation is an overall trend of change rising.

(2) And judging that the second parameter is abnormal in the first historical time period when the overall change trend is reduced, and otherwise, judging that the second parameter is normal in the first historical time period.

The smaller the second parameter corresponding to the second preset judgment condition is, the more favorable the scene of the first object is. At this time, the second abnormality information may indicate that the second parameter is abnormal within the first history time period and that the abnormal situation is a general trend of change that is decreasing.

(3) And judging that the second parameter in the first historical time period is abnormal if the value of the second parameter in at least m time units in the first historical time period is less than or equal to a second preset value, or judging that the second parameter in the first historical time period is normal if the value of the second parameter in at least m time units in the first historical time period is less than or equal to the second preset value. Wherein M is a positive integer greater than or equal to 1 and less than M, and M is a total number of time units included in the first history time period. The second preset value may be an average of values of the second parameter for a consecutive plurality of time units before the first history period.

The larger the second parameter corresponding to the second preset judgment condition is, the more favorable the scene of the first object is.

At this time, the second abnormality information may indicate that the second parameter is abnormal within the first history period and the abnormal condition is m in the first history period₁The value of the second parameter in each time unit is less than or equal to a second preset value, and m can be indicated₁A time unit. m is₁M is greater than or equal to M and less than or equal to M.

(4) And judging that the second parameter in the first historical time period is abnormal if the value of the second parameter in at least m time units in the first historical time period is larger than or equal to a second preset value, or judging that the second parameter in the first historical time period is normal if the value of the second parameter in at least m time units in the first historical time period is not larger than or equal to the second preset value. M is a positive integer greater than or equal to 1 and less than M, which is the total number of time units included in the first history period. Wherein the second preset value may be an average value of values of the second parameter of consecutive time units before the first history time period.

The smaller the second parameter corresponding to the second preset judgment condition is, the more favorable the scene of the first object is.

At this time, the second abnormality information may indicate that the second parameter is abnormal within the first history period and the abnormal condition is m in the first history period₂The value of the second parameter in each time unit is greater than or equal to a second preset value, and m can be indicated₂A time unit. m is₂M is greater than or equal to M and less than or equal to M.

(5) And judging that the second parameter in the first historical time period is abnormal if the absolute value of the ring ratio of the value of the second parameter in at least m time units in the first historical time period to the second time period is greater than or equal to a third preset value, otherwise, judging that the second parameter in the first historical time period is normal. At this time, the second time period may be carried in the analysis request, or may be preset.

For any first time unit included in the first historical time period, the calculation method of the ring ratio of the first value of the second parameter under the first time unit relative to the second time period is as follows: (the first value-the average value of the second parameter over the second time period)/the average value of the second parameter over the second time period.

At this time, the second abnormality information may indicate that the second parameter is abnormal within the first history period and that the abnormal condition is that m exists in the first history period₃The absolute value of the second parameter in a time unit relative to the ring ratio value for the second time period is greater than or equal to a third predetermined value, and may also indicate that m₃A time unit. m is₃M is greater than or equal to M and less than or equal to M.

(6) And judging that the second parameter in the first historical time period is abnormal if the absolute value of the average value of the second parameter in the first historical time period relative to the ring ratio of the second time period is greater than or equal to a fourth preset value, otherwise, judging that the second parameter in the first historical time period is normal. At this time, the second time period may be carried in the analysis request, or may be preset.

The ring ratio for the average of the second parameter over the first historical period of time relative to the second period of time is calculated as follows: (average of the second parameter over the first historical period-average of the second parameter over the second period)/average of the second parameter over the second period.

At this time, the second abnormality information may indicate that the second parameter is abnormal over the first history period and the abnormal condition is that an absolute value of an average value of the second parameter with respect to a loop ratio value of the second period over the first history period is greater than or equal to a fourth preset value.

Step S503, the server sends the second abnormal information to the first terminal device.

It is understood that, if the server analyzes that the second parameter is normal in the first history period, the server sends information that the second parameter is normal in the first history period to the first terminal device.

And step S504, the first terminal device displays the abnormal condition of the second parameter in the first historical time period based on the second abnormal information.

It can be understood that, if the server sends the information that the second parameter is normal in the first history period to the first terminal device, the first terminal device displays the information that the second parameter is normal in the first history period.

In addition, for the parameters in the preset parameter set, in addition to automatically predicting the predicted values of the parameters in a plurality of time units in the next period, the method in the embodiment may also be used to analyze whether the parameters are normal in the historical time period after receiving the analysis request from the user.

The embodiment provides a method for including partial parameters affecting the first object in the preset set of parameters, analyzing the value of the second parameter in the first historical time period for the second parameter not included in the preset parameter set, and analyzing the value of the second parameter in the first historical time period when the user triggers, so that the power consumption of the server is reduced.

It can be understood that, when the server analyzes the predicted value of the second parameter in the first time period based on the second preset judgment condition of the second parameter, and determines that the second parameter is normal in the first time period, the server sends the information that the second parameter is normal in the first time period to the terminal device.

In addition, when the server analyzes the value of the second parameter in the first historical time period based on the second preset judgment condition of the second parameter to obtain second abnormal information of the second parameter in the first historical time period, the server can also analyze the reason causing the abnormality of the second parameter in the first historical time period so as to assist the user to take corresponding measures to enable the second parameter to return to normal, and further improve the object maintenance reliability. The data processing method in this case will be described below with specific examples. Fig. 6 is a fifth flowchart of a data processing method provided in the embodiment of the present application, and referring to fig. 6, the method of the embodiment includes:

step S601, the server determines a second target attribute causing the second parameter abnormality in the first history time period according to the multiple attributes of the user corresponding to the user request received in the first history time period.

The user request in this embodiment is a user request that can affect the second parameter of the first object.

The user corresponding to the user request refers to the user who initiates the user request. Each user initiating the user request has various attributes, which are explained with reference to the embodiment shown in fig. 4 and will not be described herein.

In one approach, the server determines a second target attribute that caused the second parameter to be abnormal for the first historical period of time, including b 1-b 2 as follows:

b1, for each attribute, the server acquires the influence coefficient of the attribute on the second parameter.

The specific method for acquiring the influence coefficient of the attribute on the second parameter by the server refers to a method for acquiring the influence coefficient of the attribute on the first parameter by the server in the embodiment shown in fig. 4, which is not described herein again.

b2, determining a second target attribute according to the influence coefficient of various attributes on the second parameter.

The specific method for determining the second target attribute by the server according to the influence coefficients of the various attributes on the second parameter refers to a method for determining the first target attribute according to the influence coefficients of the various attributes on the first parameter in the embodiment shown in fig. 4, which is not described herein again.

Step S602, the server sends the second target attribute to the first terminal device.

And step S603, the first terminal equipment displays the second target attribute.

In the method of the embodiment, the server can analyze the reason causing the second parameter to be abnormal in the first historical time period and send the reason to the first terminal device, so that the user can timely know the reason causing the second parameter to be abnormal in the first historical time period, the user is assisted to take corresponding measures to enable the second parameter to return to normal, and the object maintenance reliability is further improved.

The application processing method according to the present application is explained above, and the apparatus according to the present application is explained below.

Fig. 7 is a schematic diagram of a data processing apparatus according to an embodiment of the present application. As shown in FIG. 7, the apparatus may be a server or may be a component of a server (e.g., an integrated circuit, a chip, etc.). The apparatus may be the first terminal device, or may be a component (e.g., an integrated circuit, a chip, etc.) of the first terminal device. The apparatus includes a processing module 702 (processing unit). Optionally, a transceiver module 701 (transceiver unit) and a storage module 703 (storage unit) may also be included.

In one possible implementation, the data processing apparatus may include a transceiver module 701 and a processing module 702. The data processing device is applied to a server.

The processing module 702 is configured to obtain, based on a user request for a first object sent by at least one client and received in a first period, values of a first parameter in multiple time units included in the first period, where the user request can affect the values of the first parameter of the first object; the processing module 702 is further configured to predict, according to the historical values of the first parameter in the multiple time units, a predicted value of the first parameter in the multiple time units included in a second period, where the second period is a next period of the first period.

In a possible implementation, the processing module 702 is specifically configured to: obtaining the predicted value by using a neural network model by using the historical value; the neural network model is trained based on a plurality of training samples, and the training samples comprise numerical values of the first parameter in a plurality of time units respectively included in two adjacent historical periods.

In a possible implementation manner, the processing module 702 is further configured to analyze the predicted value based on a preset determination condition of the first parameter, so as to obtain first abnormal information of the first parameter in the second period; the transceiver module 701 is configured to send the first exception information to a terminal device.

In a possible implementation manner, after the processing module 702 obtains the first exception information of the first parameter in the second period: the processing module 702 is further configured to determine, according to multiple attributes of the user corresponding to the user request, a target attribute that causes the first parameter to be abnormal in the second period; the transceiver module 701 is further configured to send the target attribute to a terminal device.

In a possible implementation, the processing module 702 is specifically configured to: for each attribute, acquiring an influence coefficient of the attribute on the first parameter; and determining the target attribute from the plurality of attributes according to the influence coefficients of various attributes on the first parameter.

In a possible implementation, the processing module 702 is specifically configured to: acquiring at least one category corresponding to the attribute; and acquiring the influence coefficient of the attribute on the first parameter according to the total number of the users and the number of the users in each category.

In one possible implementation, before the processing module 702 predicts the predicted value of the first parameter in the plurality of time units included in the second period according to the historical values of the first parameter in the plurality of time units: the processing module 702 is further configured to receive a prediction request from a terminal device, where the prediction request is used to request prediction of predicted values of the first parameter in a plurality of time units included in the second period; the transceiver module 701 is further configured to send the predicted values of the first parameter in the multiple time units included in the second period to the terminal device.

In a possible implementation manner, the transceiver module 701 is configured to receive an analysis request from a terminal device, where the analysis request is used to analyze a value of a second parameter in a first historical time period, and the second parameter does not belong to the preset parameter set; the processing module 702 is further configured to respond to the analysis request, and analyze a value of the second parameter in the first historical time period to obtain second abnormal information of the second parameter in the first historical time period; the transceiver module 701 is further configured to send the second abnormal information to a terminal device.

In a possible implementation manner, the processing module 702 is further configured to obtain a predicted variation curve of the first parameter in the second period according to the predicted value; the transceiver module 701 is configured to send the predicted change curve to a terminal device.

In one possible embodiment, the first object is a finance-related object.

The apparatus of this embodiment may be configured to execute the technical solution corresponding to the server in the foregoing method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.

Fig. 8 is a schematic view of an electronic device according to an embodiment of the present application. As shown in fig. 8, the electronic device 800 may be used to implement the method described in the above method embodiment, and refer to the description in the above method embodiment specifically. The electronic device 800 may be a server or a first terminal device

The electronic device 800 may comprise one or more processors 801, which processors 801 may also be referred to as processing units, controlling the execution of the methods in the above-described method embodiments. The processor 801 may be a general purpose processor, a special purpose processor, or the like. For example, a baseband processor, or a central processor. The baseband processor may be configured to process communication protocols and communication data, and the central processor may be configured to control the communication device, execute software programs, and process data of the software programs.

Optionally, the processor 801 may also be populated with instructions 803 or data (e.g., intermediate data). Wherein the instructions 803 may be executed by the processor, so that the electronic device 800 performs the method described in the above method embodiment.

Optionally, the electronic device 800 may include one or more memories 802, on which instructions 804 may be stored, and the instructions may be executed on the processor, so that the electronic device 800 performs the methods described in the above method embodiments.

Optionally, the memory may also store data. The processor 801 and the memory 802 may be provided separately or may be integrated together.

Optionally, the electronic device 800 may further include a transceiver 805 and/or an antenna 806. The transceiver 805 may be referred to as a transceiver unit, a transceiver, a transceiving circuit, a transceiver, or the like, and is used for implementing transceiving functions of a communication device.

The processor 801 and transceiver 805 described herein may be implemented on an Integrated Circuit (IC), an analog IC, a Radio Frequency Integrated Circuit (RFIC), a mixed signal IC, an Application Specific Integrated Circuit (ASIC), a Printed Circuit Board (PCB), an electronic device, or the like. The processor and transceiver may also be fabricated using various 1C process technologies, such as Complementary Metal Oxide Semiconductor (CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (PMOS), Bipolar Junction Transistor (BJT), bipolar CMOS (bicmos), silicon germanium (SiGe), gallium arsenide (GaAs), and the like.

It should be understood that the processor mentioned in the embodiments of the present Application may be a Central Processing Unit (CPU), and may also be other general purpose processors, Digital Signal Processors (DSP), Application Specific Integrated Circuits (ASIC), Field Programmable Gate Arrays (FPGA) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will also be appreciated that the memory referred to in the embodiments of the application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

An embodiment of the present application further provides a computer storage medium, including: computer-executable instructions, when the program or the instructions runs on a computer, the method corresponding to the server or the first terminal device in any of the above method embodiments is executed.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims. It will be understood that the present disclosure is not limited to the precise arrangements 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. A data processing method is applied to a server and comprises the following steps:

the method comprises the steps that values of a first parameter under a plurality of time units included in a first period are obtained based on a user request aiming at a first object and received in the first period, wherein the user request can influence the values of the first parameter of the first object;

and predicting the predicted values of the first parameter in a plurality of time units in a second period according to the historical values of the first parameter in the plurality of time units, wherein the second period is the next period of the first period.

2. The method of claim 1, wherein predicting the second period from historical values of the first parameter for the plurality of time units comprises predicting values of the first parameter for the plurality of time units based on the second period, comprising:

obtaining the predicted value by using a neural network model by using the historical value;

the neural network model is trained based on a plurality of training samples, and the training samples comprise numerical values of the first parameter in a plurality of time units respectively included in two adjacent historical periods.

3. The method of claim 1, further comprising:

analyzing the predicted value based on a preset judgment condition of the first parameter to obtain first abnormal information of the first parameter in the second period;

and sending the first abnormal information to the terminal equipment.

4. The method of claim 3, further comprising, after obtaining the first anomaly information for the first parameter during the second period:

determining a target attribute causing the first parameter exception in the second period according to various attributes of a user corresponding to the user request;

and sending the target attribute to the terminal equipment.

5. The method of claim 4, wherein determining the target class attribute that caused the first parameter exception during the second period comprises:

for each attribute, acquiring an influence coefficient of the attribute on the first parameter;

and determining the target attribute from the plurality of attributes according to the influence coefficients of various attributes on the first parameter.

6. The method of claim 5, wherein obtaining the influence coefficient of the attribute on the first parameter comprises:

acquiring at least one category corresponding to the attribute;

and acquiring the influence coefficient of the attribute on the first parameter according to the total number of the users and the number of the users in each category.

7. The method according to any of claims 1-6, further comprising, before predicting the predicted value of the first parameter for a plurality of time units included in the second period based on the historical values of the first parameter for the plurality of time units, the step of:

receiving a prediction request from a terminal device, wherein the prediction request is used for requesting prediction of a prediction value of the first parameter in a plurality of time units included in the second period;

and sending the predicted values of the first parameter under a plurality of time units included in the second period to the terminal equipment.

8. The method according to any one of claims 1 to 6, wherein the first parameter is a parameter in a preset parameter set.

9. The method of claim 8, further comprising:

receiving an analysis request from a terminal device, wherein the analysis request is used for analyzing a value of a second parameter in a first historical time period, and the second parameter does not belong to the preset parameter set;

responding to the analysis request, analyzing the value of the second parameter in the first historical time period to obtain second abnormal information of the second parameter in the first historical time period;

and sending the second abnormal information to the terminal equipment.

10. The method of any one of claims 1 to 6, further comprising:

obtaining a predicted change curve of the first parameter in the second period according to the predicted value;

and sending the predicted change curve to the terminal equipment.

11. The method of any one of claims 1 to 6, further comprising:

and sending the prediction value to the terminal equipment.

12. A data processing method is applied to a server and comprises the following steps:

acquiring numerical values of the first parameter in a plurality of time units included in a first period;

according to values of the first parameter in a plurality of time units included in a first period, obtaining predicted values of the first parameter in a plurality of time units included in a second period, wherein the second period is the next period of the first period.

13. A data processing apparatus, comprising:

the processing module is used for acquiring numerical values of a first parameter under a plurality of time units included in a first period based on a user request aiming at a first object and received by at least one client in the first period, wherein the user request can influence the numerical values of the first parameter of the first object;

the processing module is further configured to predict, according to the historical values of the first parameter in the multiple time units, a predicted value of the first parameter in the multiple time units included in a second period, where the second period is a next period of the first period.

14. A data processing apparatus, comprising:

the processing module is used for acquiring numerical values of the first parameter in a plurality of time units included in a first period;

the processing module is further configured to obtain predicted values of the first parameter in multiple time units included in a second period according to the values of the first parameter in multiple time units included in the first period, where the second period is a next period of the first period.

15. A computer device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the data processing method of any one of claims 1 to 12.

16. A computer-readable storage medium, having stored thereon computer-executable instructions for implementing a data processing method according to any one of claims 1 to 12 when executed by a processor.