Parameter determination method and device, storage medium and electronic device

Abstract

The embodiment of the invention provides a parameter determination method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining operation data of a target account in a target application, determining a parameter prediction request according to the operation data, and obtaining target prediction data; determining trend data of the target object according to whether the target prediction data meets a basic analysis condition; determining a target critical value of the target parameter in a middle time period of the future time period according to the historical data; inputting a target pricing factor in the target prediction data into the three-factor pricing model to obtain a change interval of the target parameter in the future time, the target pricing factor being determined by performing correlation analysis on a group of pricing factors in the historical data and the target parameter; and generating a target prediction result based on the trend data, the target critical value and the change interval, and generating a prompt message associated with the target parameter based on the target prediction result. Through the method and the device, the technical problem of relatively low prediction accuracy of the target parameter is solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a method, device, storage medium, and electronic device for determining a parameter. Background Art

[0002] At present, in related technologies, target parameters often rely on manual prediction. In other words, staff are required to evaluate target parameters based on a large amount of historical data and manual experience. This leads to the target parameters being subject to the subjective influence of staff. Different staff members predict different target parameters, which makes the target parameters not very available and cannot be applied to actual business systems, resulting in a technical problem of low prediction accuracy of target parameters.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a parameter determination method, device, storage medium and electronic device to at least solve the technical problem of low prediction accuracy of target parameters.

[0005] According to one aspect of the present application, a parameter determination method is provided, comprising: obtaining operation data of a target account in a target application, determining a parameter prediction request based on the operation data, wherein the parameter prediction request matches a parameter type associated with the operation data; in response to the parameter prediction request, obtaining target prediction data, wherein the target prediction data includes basic data predicted for a future time period; determining trend data of a target object based on whether the target prediction data meets basic analysis conditions, wherein the trend data is used to indicate a change trend of a target parameter of the target object in the future time period, wherein the basic analysis conditions are determined by historical data of the target object in a historical time period; determining a target critical value of the target parameter in an intermediate time period of the future time period based on the historical data, wherein the target critical value is a value that indicates a change trend of a target parameter of the target object in the future time period ... The value represents the maximum or minimum value of the target parameter in the intermediate time period; the target pricing factor in the target prediction data is input into the three-factor pricing model to obtain the change range of the target parameter in the future time, wherein the three-factor pricing model is determined by regression analysis modeling of the target pricing factor, and the target pricing factor is determined by correlation analysis of a set of pricing factors in the historical data and the target parameter; a target prediction result is generated based on the trend data, the target critical value and the change range, wherein the target prediction result includes the target parameter predicted for the future time period; a prompt message associated with the target parameter is generated based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application.

[0006] According to another aspect of the present application, a parameter determination device is provided, comprising: a first acquisition module, used to obtain operation data of a target account in a target application, and determine a parameter prediction request based on the operation data, wherein the parameter prediction request matches the parameter type associated with the operation data; a second acquisition module, used to respond to the parameter prediction request and obtain target prediction data, wherein the target prediction data includes basic data predicted for a future time period; a first determination module, used to determine trend data of a target object based on whether the target prediction data meets basic analysis conditions, wherein the trend data is used to indicate a change trend of a target parameter of the target object in the future time period, and the basic analysis conditions are determined by historical data of the target object in a historical time period; a second determination module, used to determine a target critical value of the target parameter in an intermediate time period of the future time period based on the historical data, wherein the target prediction data includes basic data predicted for a future time period; The target critical value represents the maximum or minimum value of the target parameter in the intermediate time period; a third determination module is used to input the target pricing factor in the target prediction data into a three-factor pricing model to obtain the change range of the target parameter in the future time, wherein the three-factor pricing model is determined by regression analysis modeling of the target pricing factor, and the target pricing factor is determined by correlation analysis of a group of pricing factors in the historical data and the target parameter; a first generation module is used to generate a target prediction result based on the trend data, the target critical value and the change range, wherein the target prediction result includes the target parameter predicted for the future time period; a second generation module is used to generate a prompt message associated with the target parameter based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application.

[0007] Optionally, the device is also used for: inputting the target pricing factor in the target prediction data into the three-factor pricing model to obtain the change interval of the target parameter in the future time, performing correlation analysis on the set of pricing factors according to the historical data to determine a first set of correlation coefficients; determining a first pricing factor according to the first set of correlation coefficients, wherein the correlation coefficient corresponding to the first pricing factor is the correlation coefficient in the first set of correlation coefficients that meets a preset sorting condition, and the target pricing factor includes the first pricing factor; performing regression analysis modeling on the first pricing factor to determine the three-factor pricing model.

[0008] Optionally, the device is also used to: update the historical data periodically or at a preset time point; in response to the historical data being updated, re-perform correlation analysis on the set of pricing factors based on the updated historical data to determine a second set of correlation coefficients; determine a second pricing factor based on the second set of correlation coefficients, wherein the correlation coefficient corresponding to the second pricing factor is the correlation coefficient in the second set of correlation coefficients that meets the preset sorting condition, and the target pricing factor includes the second pricing factor; perform regression analysis modeling on the second pricing factor to update the three-factor pricing model.

[0009] Optionally, the device is used to determine the trend data of the target object according to whether the target prediction data meets the basic analysis conditions in the following manner: determine the change dependency relationship between the target parameters in the historical data and the target supply and demand parameters, wherein the basic analysis conditions include the change dependency relationship; determine the future supply and demand parameters corresponding to the target supply and demand parameters according to the target prediction data; and determine the trend data based on the future supply and demand parameters and the change dependency relationship.

[0010] Optionally, the device is used to determine the change dependency relationship between the target parameter and the target supply and demand parameter in the historical data in the following manner: obtain the target parameter, supply parameter and demand parameter of at least two adjacent historical time periods in the historical data, wherein the target supply and demand parameters include the supply parameter and the demand parameter; when the supply parameter corresponding to the at least two adjacent historical time periods is greater than the demand parameter, determining that the change dependency relationship indicates that the target parameter shows a downward trend in the future time period; when the supply parameter corresponding to the at least two adjacent historical time periods is less than the demand parameter, determining that the change dependency relationship indicates that the target parameter shows an upward trend in the future time period.

[0011] Optionally, the device is used to determine the target critical value of the target parameter in the future time period based on historical data in the following manner: determine the lowest value, the highest value and the target golden section value of the target parameter in the historical time period based on the historical data; determine the change trend of the target parameter in the intermediate time period based on the target golden section value; determine the target critical value based on the change trend, the lowest value or the highest value and the periodic floating ratio of the target parameter.

[0012] Optionally, the device is used to determine the lowest value, the highest value and the target golden section value of the target parameter in the historical period according to the historical data in the following manner: draw a technical analysis chart according to the historical data, wherein the technical analysis chart includes a target broken line, and the target broken line is used to indicate the change of the target parameter in the historical data according to a preset period; determine the lowest value, the highest value and the target golden section value based on the target broken line, wherein the target golden section value represents the value corresponding to the target parameter indicated by the golden section point of the target interval with the lowest value as the lower limit and the highest value as the upper limit; the device is used to determine the change trend of the target parameter in the intermediate period according to the target golden section value in the following manner: obtain the target value of the target parameter in the N time periods after the target time period corresponding to the target golden section point The value corresponding to the target parameter, wherein N is a positive integer; when the value corresponding to the target parameter in N time periods after the target time period is greater than or equal to the target golden section value, the change trend is determined to be increasing; when the value corresponding to the target parameter in N time periods after the target time period is less than the target golden section value, the change trend is determined to be decreasing; the device is used to determine the target critical value according to the change trend, the minimum value or the maximum value and the periodic floating ratio of the target parameter in the following manner: when the change trend indicates an increase, the maximum value indicated by the target critical value is determined according to the maximum value and the periodic floating ratio; or, when the change trend indicates a decrease, the minimum value indicated by the target critical value is determined according to the minimum value and the periodic floating ratio.

[0013] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0014] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0015] In an embodiment of the present application, by obtaining the operation data of the target account in the target application, a parameter prediction request is determined according to the operation data, wherein the parameter prediction request matches the parameter type associated with the operation data, and in response to the parameter prediction request, target prediction data is obtained, wherein the target prediction data includes basic data obtained by predicting a future time period; trend data of the target object is determined according to whether the target prediction data meets basic analysis conditions, wherein the trend data is used to indicate the changing trend of the target parameter of the target object in the future time period, and the basic analysis conditions are determined by the historical data of the target object in the historical time period; the target critical value of the target parameter in the middle time period of the future time period is determined according to the historical data, wherein the target critical value represents the maximum value or minimum value of the target parameter in the middle time period; the target pricing factor in the target prediction data is input into the three-factor pricing model , obtain the change range of the target parameter in the future time, wherein the three-factor pricing model is determined by regression analysis modeling of the target pricing factor, and the target pricing factor is determined by correlation analysis of a set of pricing factors in historical data and the target parameter; generate the target prediction result based on the trend data, the target critical value and the change range, wherein the target prediction result includes the target parameter obtained by predicting the future time period, and generate a prompt message associated with the target parameter based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application, thereby achieving the purpose of expanding the generation method of the target parameter, optimizing the generation process of the target parameter, and further achieving the technical effect of improving the practicality and availability of the target parameter, meeting a variety of application scenarios, and thus solving the technical problem of low prediction accuracy of the target parameter. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a hardware structure block diagram of a mobile terminal according to a method for determining a parameter in an embodiment of the present application;

[0017] Figure 2 is a flow chart of a method for determining parameters according to an embodiment of the present application;

[0018] Figure 3 is a flow chart of a method for determining parameters according to an embodiment of the present application;

[0019] Figure 4 is a flow chart of another method for determining parameters according to an embodiment of the present application;

[0020] Figure 5 It is a structural block diagram of a parameter determination device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0023] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretation:

[0024] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for determining a parameter in an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and a terminal device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0025] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the parameter determination method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0026] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0027] Optionally, in this embodiment, the method for determining the above parameters may also be implemented by a server, or implemented by the terminal device and the server together.

[0028] The above is only an example and is not specifically limited in this embodiment.

[0029] Optionally, as an optional implementation, Figure 2 is a flow chart of a method for determining parameters according to an embodiment of the present application, such as Figure 2 As shown, the method for determining the above parameters includes:

[0030] S202, obtaining operation data of the target account in the target application, and determining a parameter prediction request according to the operation data, wherein the parameter prediction request matches a parameter type associated with the operation data;

[0031] S204, in response to the parameter prediction request, obtaining target prediction data, wherein the target prediction data includes basic data predicted for a future period;

[0032] Optionally, in this embodiment, the target account may include but is not limited to a personal account, a corporate account, a system account, etc., the target application may include but is not limited to a social media application, an e-commerce platform, a financial service application, etc., the operation data may be understood as user action data (such as clicks, browsing, searching, etc.), transaction records, user preference settings, etc., and may include but is not limited to logging into the business system through a front-end device to issue the parameter prediction request, the front-end device may include but is not limited to a mobile phone, a computer, a tablet, etc., the business system may include but is not limited to a website system, an independent application system, a cloud service system deployed on a cloud server, etc., the parameter prediction request may include but is not limited to requesting the price, content, form, etc. of a certain object, and the basic data may include but is not limited to the price range of objects in region A predicted by website A in the next year, events that will occur in region A in the future period predicted by website A, etc.

[0033] Among them, cloud technology refers to a hosting technology that unifies hardware, software, network and other resources within a wide area network or local area network to achieve data calculation, storage, processing and sharing.

[0034] Cloud computing refers to the delivery and use model of IT infrastructure, which means obtaining required resources through the network in an on-demand and easily scalable manner; in a broad sense, cloud computing refers to the delivery and use model of services, which means obtaining required services through the network in an on-demand and easily scalable manner. This service can be related to IT and software, the Internet, or other services. Cloud computing is the product of the development and integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing.

[0035] With the development of the Internet, real-time data streams, and the diversification of connected devices, as well as the demand for search services, social networks, mobile commerce, and open collaboration, cloud computing has developed rapidly. Different from the previous parallel distributed computing, the emergence of cloud computing will promote revolutionary changes in the entire Internet model and enterprise management model from a conceptual perspective.

[0036] Cloud security refers to the general term for security software, hardware, users, organizations, and security cloud platforms based on cloud computing business model applications. Cloud security integrates emerging technologies and concepts such as parallel processing, grid computing, and unknown virus behavior judgment. Through a large number of networked clients, it monitors abnormal software behavior in the network, obtains the latest information on Trojans and malicious programs on the Internet, and sends it to the server for automatic analysis and processing, and then distributes virus and Trojan solutions to each client.

[0037] The main research directions of cloud security include: 1. Cloud computing security, which mainly studies how to ensure the security of the cloud itself and various applications on the cloud, including cloud computer system security, secure storage and isolation of user data, user access authentication, information transmission security, network attack protection, compliance auditing, etc.; 2. Cloudification of security infrastructure, which mainly studies how to use cloud computing to build and integrate security infrastructure resources and optimize security protection mechanisms, including building a large-scale security event, information collection and processing platform through cloud computing technology, realizing the collection and correlation analysis of massive information, and improving the control ability of security events and risk control capabilities of the entire network; 3. Cloud security services, which mainly studies various security services provided to users based on cloud computing platforms, such as antivirus services.

[0038] For example, taking the banking system as an example, the parameter type is gold, and the above parameter prediction request indicates a prediction of the gold price in region A in the next year. Then, the above target prediction data may include but is not limited to the currency exchange rate in region A in the next year predicted by various websites, systems and other channels, the currency exchange rate in region B in the next year, and events that will occur in region A in the next year, for example, natural disasters in region A in the next year, etc. It can be understood that the target prediction data is related to the gold price. For example, the gold price will be affected by the currency exchange rate in region A.

[0039] S206, determining trend data of the target object according to whether the target prediction data meets the basic analysis conditions, wherein the trend data is used to indicate the change trend of the target parameter of the target object in the future period, and the basic analysis conditions are determined by the historical data of the target object in the historical period;

[0040] Optionally, in an embodiment of the present application, the target object may include but is not limited to gold, virtual currency, virtual items, etc. The target parameter corresponds to the target object, and may include but is not limited to attribute information of the target object, such as the price of the target object, the weight of the target object, the size of the target object, etc. The basic analysis condition may include but is not limited to multiple analysis conditions, which are used to judge the changing trend of the target object in the future time period. For example, the target object is gold, the target parameter is the price of gold, the basic analysis condition A is that when the supply of gold in area A is greater than the shipment of gold in area A, the price of gold in area A shows a downward trend, and the basic analysis condition B is that when the supply of gold in area A is less than the shipment of gold in area A, the price of gold in area A shows an upward trend.

[0041] Further, assuming that the target forecast data shows that the gold supply in region A in the future period will be greater than the gold shipment in region A, then, correspondingly, according to basic analysis condition A, the price of gold in the future period will decrease. Conversely, assuming that the target forecast data shows that the gold supply in region A in the future period will be less than the gold shipment in region A, then, correspondingly, according to basic analysis condition B, the price of gold in the future period will increase. The above trend data includes but is not limited to the target parameter value becoming larger, the target parameter value becoming smaller. In combination with examples, the above trend data may include but is not limited to the target parameter showing a downward trend in the future period, the target parameter showing an upward trend in the future period, the target parameter remaining unchanged in the future period, etc.

[0042] For another example, the above basic analysis conditions indicate that if a natural disaster occurs, the change trend of the target parameters of the target object will be a downward trend. Then, if the target prediction data includes data A indicating that a natural disaster will occur in the future period, then, correspondingly, the change trend of the target parameters of the target object will be a downward trend.

[0043] Specifically, the above-mentioned basic analysis conditions may include but are not limited to being determined by analyzing the above-mentioned historical data, and the historical data may include but are not limited to relevant attribute information of the above-mentioned target object in the historical period, for example, the price of the target object in the historical period, the weight of the target object in the historical period, the size of the target object in the historical period, natural disasters that occurred in the historical period, the currency exchange rate in the historical period, the supply of the target object in the historical period, the shipment volume of the target object in the historical period, etc. Furthermore, parameters corresponding to the above-mentioned target parameters can also be obtained in the historical data. For example, the target parameter represents the price of the target object in the future period, then the price of the target object in the historical period can be included in the historical data.

[0044] Furthermore, assuming that the price of the target object in the historical data during the historical period is parameter A, then regression analysis can be performed on parameter A and each parameter in the historical data except parameter A to obtain the dependency relationship between parameter A and other parameters, and then, the above-mentioned basic analysis conditions are generated. For example, after regression analysis, the dependency relationship between parameter A and parameter B is that when the value of parameter B increases during the historical period, the value of parameter A decreases. Therefore, there is an analysis condition in the basic analysis conditions that when parameter B increases, the change trend of parameter A is a downward trend.

[0045] S208, determining a target critical value of the target parameter in the middle period of the future period according to the historical data, wherein the target critical value represents the maximum value or minimum value of the target parameter in the middle period;

[0046] Optionally, in an embodiment of the present application, the above-mentioned intermediate time period may include but is not limited to any time period in the above-mentioned future time period, and the above-mentioned target critical value may be understood as the upper limit value or the lower limit value of the target parameter in the intermediate time period.

[0047] For example, Figure 3 is a flow chart of a method for determining parameters according to an embodiment of the present application, such as Figure 3 As shown in the figure, a change trend chart can be generated according to the historical values ​​corresponding to the target parameters at each time point in the historical data. The target parameter is taken as an example, where the price of the target object is price A in the first month of the historical period, and the price of the target object is price B in the 12th month of the historical period. Figure 3 In the figure, the horizontal axis represents the historical period, the left vertical axis represents the price of the target object at any time point in the historical period, and the right vertical axis represents the position of the price of the target object at any time point in the historical period in the historical change interval. The historical change interval represents the price change range of the target object in the historical period. For example, the highest price of the target object in the historical period is 110 and the lowest is 10. The historical change interval is [10,110]. The price of the target object corresponding to time point A in the historical period is 50. Then, the corresponding percentage of the historical value can be determined by (50-10) / (110-10). The percentage of the price of the target object corresponding to time point A is 40%.

[0048] Furthermore, taking gold as the target object and the gold price as the target parameter, the gold price of each month in the historical period can be obtained according to the historical data, and then, the following is generated according to the historical data: Figure 3 As shown in the gold price trend chart, the highest gold price in the historical period is 1550, the gold support point is set to 0.618, the golden section point is 0.382, and the floating percentage of the gold price in the historical period is half of the golden section point, that is, the floating percentage is 0.191 (19.10%). The values ​​of the golden support point and the golden section point can be set flexibly according to Figure 3 It can be obtained that if there is a time point from the 11th to the 13th month when the corresponding percentage of the gold price exceeds 0.618, that is, the gold price exceeds 1430, it can be determined that the gold price will show an upward trend in the future period. The above target critical value can be determined by (upward percentage + 1) * the highest gold price in the historical period, and the target critical value is 1769.

[0049] S210, inputting the target pricing factor in the target forecast data into a three-factor pricing model to obtain a change range of the target parameter in the future, wherein the three-factor pricing model is determined by performing regression analysis modeling on the target pricing factor, and the target pricing factor is determined by performing correlation analysis on a set of pricing factors in historical data and the target parameter;

[0050] Optionally, in an embodiment of the present application, the above-mentioned target pricing factor can be understood as a pricing factor that affects the above-mentioned target parameter. For example, if parameter A becomes larger and the target parameter becomes smaller, then parameter A is the target pricing factor, and the target pricing factor may include but is not limited to multiple factors. For example, if parameter A becomes larger and the target parameter becomes smaller, if parameter B becomes larger and the target parameter becomes smaller, if parameter C becomes larger and the target parameter becomes larger, then the target pricing factor may be composed of parameter A, parameter B, and parameter C, and the target pricing factor may include but is not limited to any parameter in the above-mentioned target prediction data.

[0051] Specifically, assuming that the target object is gold and the target parameter is the gold price, the target forecast data includes the A virtual currency index predicted for the future period, the B virtual currency index predicted for the future period, the C virtual currency index predicted for the future period, the A bond yield predicted for the future period, the B bond yield predicted for the future period, the C bond yield predicted for the future period, the A region GDP predicted for the future period, the B region GDP predicted for the future period, and the C region GDP predicted for the future period. Then, the above target pricing factors can be determined, including but not limited to, through the following steps:

[0052] S1, obtaining the gold price, A virtual currency index, B virtual currency index, C virtual currency index, A bond yield, B bond yield, C bond yield, A regional GDP, B regional GDP, C regional GDP at each time point in the corresponding historical period in the historical data, wherein A virtual currency index, B virtual currency index, C virtual currency index, A bond yield, B bond yield, C bond yield, A regional GDP, B regional GDP, C regional GDP at each time point in the historical period represents the above-mentioned set of pricing factors;

[0053] S2, respectively performing correlation analysis on the A virtual currency index, the B virtual currency index, the C virtual currency index, the A bond yield, the B bond yield, the C bond yield, the A regional GDP, the B regional GDP, the C regional GDP and the historical gold price, which may include but is not limited to using statistical methods (Spearman correlation coefficient analysis, linear regression analysis, etc.) to analyze the correlation between the regional GDP and the historical gold price, and obtain a set of correlation coefficients;

[0054] S3, the parameters corresponding to the three largest correlation coefficients are determined as the target pricing factors.

[0055] For example, the correlation coefficient between virtual currency index A and historical gold prices is 80, the correlation coefficient between virtual currency index B and historical gold prices is 20, the correlation coefficient between virtual currency index C and historical gold prices is 30, the correlation coefficient between bond yield B and historical gold prices is 70, the correlation coefficient between bond yield C and historical gold prices is 30, the correlation coefficient between GDP of region A and historical gold prices is 10, the correlation coefficient between GDP of region B and historical gold prices is 78, and the correlation coefficient between GDP of region C and historical gold prices is 54. Then, virtual currency index A, bond yield B, and GDP of region B can be determined as target pricing factors.

[0056] Furthermore, each pricing factor in the target pricing factor is taken as an independent variable, and the target parameter is taken as the dependent variable for regression analysis to generate the above-mentioned three-factor pricing model. For example, the target pricing factor is composed of A virtual currency index, B bond yield, and B regional GDP, the target parameter is gold price, the correlation coefficient between A virtual currency index and gold price is A, the correlation coefficient between B bond yield and gold price is B, and the correlation coefficient between B regional GDP and gold price is C. Then, the three-factor pricing model can be expressed as Y = interception parameter-A*X1-B*X2-C*X3, wherein the interception parameter is determined by regression analysis modeling of the target pricing factor, X1 represents the A virtual currency index predicted for the future period, X2 represents the B bond yield predicted for the future period, and X3 represents the B regional GDP predicted for the future period. It can be understood that the correlation, fit, and adjusted fit coefficient between the target pricing factor and the target parameter are all close to 1.

[0057] Exemplarily, after obtaining the above-mentioned three-factor pricing model, the target pricing factor can be used as the model input, and the model output can be determined as the value in the above-mentioned variation range. For example, the target parameter is the gold price, and the three-factor pricing model is expressed as Y=1-2*X1-3*X2-4*X3, where X1 represents the A virtual currency index predicted for the future period, X2 represents the B bond yield predicted for the future period, and X3 represents the B regional GDP predicted for the future period. At this time, the variation range of X1 is [A1, A2], the variation range of X2 is [B1, B2], and the variation range of X3 is [C1, C2]. Then, different value combinations of X1, X2, and X3 can be input respectively, and the maximum value output by the three-factor pricing model is used as the upper limit value of the above-mentioned variation range, and the minimum value output by the three-factor pricing model is used as the lower limit value of the above-mentioned variation range.

[0058] S212, generating a target prediction result based on the trend data, the target critical value and the change interval;

[0059] S214, generating a prompt message associated with the target parameter based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application.

[0060] Optionally, in an embodiment of the present application, the above prompt message includes but is not limited to being conveyed in various ways such as voice, text, video, image, etc.

[0061] Exemplarily, assuming that the above trend data indicates that the target parameter is in an upward trend in the future period, the target critical value of the target parameter in the future period is A, and the change range of the target parameter in the future period is [B, C], then the above target prediction result may include but is not limited to being displayed in the form of text, voice, video, and image, and the content of the target prediction result may include but is not limited to the above trend data indicating that the target parameter is in an upward trend in the future period, the target critical value is A, and the change range is [B, C].

[0062] Furthermore, after the target prediction result is generated, a prompt message associated with the target parameter is generated based on the target prediction result to provide information about the target parameter status to the target account (e.g., user, system or device). The prompt message can be conveyed in a variety of ways, including voice, text, video or image.

[0063] Specifically, combined with the above example, the prompt message can be presented in the following ways: Text: Provide a description that the target parameter is expected to rise, the critical value is A, and the change range is [B, C]; Voice: Use speech synthesis technology to play the above information in voice form; Video: Make a short video to show the rising trend, critical value and change range of the target parameter; Image: Create a chart or image to intuitively show the expected changes in the target parameter.

[0064] In an exemplary embodiment, Figure 4 FIG. 1 is a flow chart of another method for determining parameters according to an embodiment of the present application. The method for determining parameters proposed in the present application can be applied to application scenarios in which a banking system performs price prediction on currencies such as gold, such as Figure 4 This may include, but is not limited to:

[0065] S402, start;

[0066] S404, obtaining forecast data related to gold prices in future periods;

[0067] S406, obtaining the change trend of the predicted gold price in the future period according to the basic analysis conditions and the historical data related to the gold price in the historical period;

[0068] S408, obtaining a target critical value of the gold price in the middle period according to historical data related to the gold price in the historical period;

[0069] S410, inputting the target pricing factor into the three-factor pricing model to obtain the change range of the gold price in the future period;

[0070] S412, the golden prediction result is obtained by comprehensively considering the change trend, target critical value and change range.

[0071] In another exemplary embodiment, taking an online course platform as an example:

[0072] S1, obtain operation data: collect user operation data on the education platform, such as the length of time spent watching videos, the time spent completing homework, the frequency of participating in discussions, etc.;

[0073] S2, parameter prediction request: Based on these operation data, predict the resources or services that users may need, such as recommending courses, learning materials, or additional tutoring time;

[0074] S3, obtain prediction data: by analyzing the user's historical learning behavior and current learning progress, predict the learning outcomes that the user may achieve in the future, such as the expected test score or the time to complete the course;

[0075] S4, determine trend data: Based on the user's historical performance, determine the user's learning trend, such as whether they are steadily improving, whether they need additional help, etc.;

[0076] S5, Determine target thresholds: Set key learning milestones, such as the number of courses that must be completed or the score that must be achieved by a certain point in time;

[0077] S6, set up a three-factor pricing model: predict the likelihood of users completing the course based on their learning efficiency, course difficulty, and available resources;

[0078] S7, generate prediction results: combine the user's learning trends, key milestones and the predictions of the three-factor model to predict the learning outcomes that the user may achieve in the future;

[0079] S8, Generate prompt messages, generate personalized learning suggestions or reminders, such as "Your performance in the math course is steadily improving, and you are expected to complete the course within the next month."

[0080] Through the embodiments of the present application, the user's operation data can be analyzed to predict learning outcomes, and personalized learning suggestions can be provided to improve the user's learning efficiency and satisfaction.

[0081] According to the embodiment of the present application, in response to a parameter prediction request, target prediction data is obtained, wherein the target prediction data includes basic data obtained by predicting a future time period; trend data of the target object is determined according to whether the target prediction data meets basic analysis conditions, wherein the trend data is used to indicate the change trend of the target parameter of the target object in the future time period, and the basic analysis conditions are determined by the historical data of the target object in the historical time period; the target critical value of the target parameter in the middle time period of the future time period is determined according to the historical data, wherein the target critical value represents the maximum value or minimum value of the target parameter in the middle time period; the target pricing factor in the target prediction data is input into the three-factor pricing model to obtain the change interval of the target parameter in the future time, wherein the three-factor pricing model is determined by regression analysis modeling of the target pricing factor, and the target pricing factor is determined by correlation analysis of a set of pricing factors in the historical data and the target parameter; the target prediction result is generated based on the trend data, the target critical value and the change interval, wherein the target prediction result includes the target parameter obtained by predicting the future time period, thereby achieving the purpose of expanding the generation method of the target parameter, optimizing the generation process of the target parameter, and further achieving the technical effect of improving the practicality and availability of the target parameter, meeting a variety of application scenarios, and thus solving the technical problem of low prediction accuracy of the target parameter.

[0082] As an optional scheme, the above method also includes: inputting the target pricing factor in the above target prediction data into the three-factor pricing model to obtain the change interval of the above target parameter in the above future time, performing correlation analysis on the above set of pricing factors according to the above historical data to determine a first set of correlation coefficients; determining the first pricing factor according to the above first set of correlation coefficients, wherein the correlation coefficient corresponding to the above first pricing factor is the correlation coefficient in the above first set of correlation coefficients that meets the preset sorting conditions, and the above target pricing factor includes the above first pricing factor; performing regression analysis modeling on the above first pricing factor to determine the above three-factor pricing model.

[0083] Optionally, in an embodiment of the present application, the above-mentioned correlation analysis may include but is not limited to Pearson correlation coefficient analysis: used to measure the strength and direction of the linear relationship between two variables, with a value range of -1 to 1, the closer the value is to 1 or -1, the stronger the correlation is, and the closer the value is to 0, the weaker the correlation is; Spearman correlation coefficient analysis: used to measure the strength and direction of the monotonic relationship between two variables, used for nonlinear relationships and ordinal variables; determination coefficient (R-square) analysis: used to measure the proportion of one variable that can be explained by another variable, with a value range of 0 to 1, the closer the value is to 1, the stronger the correlation is; Pearson chi-square test: used to measure the correlation between two categorical variables, suitable for contingency table data; linear regression analysis: used to establish a linear relationship model between two or more variables, and measure the correlation between variables through regression coefficients, etc.

[0084] Furthermore, the above-mentioned set of pricing factors can be determined by the above-mentioned historical data. For example, the above-mentioned historical data includes parameter A, and the parameter A can be determined as a factor in a set of pricing factors. After performing correlation analysis on the above-mentioned set of pricing factors, the corresponding correlation coefficients of each pricing factor can be determined as the above-mentioned first set of correlation coefficients. For example, the correlation coefficient between pricing factor A and the target parameter is 0.2, and the correlation coefficient between pricing factor B and the target parameter is 0.4, indicating that the correlation degree between pricing factor A and the target parameter is lower than the correlation degree between pricing factor B and the target parameter.

[0085] Exemplarily, the above-mentioned preset sorting condition can be understood as sorting the pricing factors in the above-mentioned group of pricing factors according to the correlation coefficient values ​​from large to small, and determining the correlation coefficients corresponding to the first three pricing factors as the correlation coefficients that meet the preset sorting condition. At this time, it can include but is not limited to determining these three pricing factors as the above-mentioned first pricing factor, as the pricing factors in the above-mentioned target pricing factor, and then performing regression analysis modeling on the target pricing factor and the target parameter to obtain a three-factor pricing model, ensuring that the three-factor pricing model can accurately generate the above-mentioned change range, so that the predicted target parameters are more credible.

[0086] As an optional solution, the method further includes: updating the historical data periodically or at a preset time point; in response to an update of the historical data, re-performing a correlation analysis on the set of pricing factors according to the updated historical data to determine a second set of correlation coefficients; determining a second pricing factor according to the second set of correlation coefficients, wherein the correlation coefficient corresponding to the second pricing factor is the correlation coefficient in the second set of correlation coefficients that satisfies the preset sorting condition, and the target pricing factor includes the second pricing factor; performing regression analysis modeling on the second pricing factor to update the three-factor pricing model.

[0087] It should be noted that it may include but is not limited to periodically obtaining the above-mentioned historical data, updating the historical data, and then using the latest historical data to perform correlation analysis on the above-mentioned set of pricing factors again, to determine the above-mentioned second set of correlation coefficients, and then, based on the second set of correlation coefficients, determine the target pricing factor, and update the three-factor pricing model. For example, historical data is obtained every 10 days, the target pricing factor is re-determined, and the three-factor pricing model is updated.

[0088] For example, the above historical data is obtained at a preset time node, and the historical data is updated. Then, the correlation analysis of the above set of pricing factors is performed again using the latest historical data to determine the above second set of correlation coefficients. Then, the target pricing factor is determined based on the second set of correlation coefficients, and the three-factor pricing model is updated. For example, historical data is obtained at 9 o'clock every Monday, the target pricing factor is re-determined, and the three-factor pricing model is updated.

[0089] Specifically, in the first period, the target pricing factors are determined to be factor A, factor B, and factor C. In the second period, the target pricing factors are re-determined to be factor A, factor B, and factor D through historical data acquired in real time. That is, in the first period, it is determined that the correlation degree between factor C and the target parameter is higher than the correlation degree between factor D and the target parameter. In the second period, it is determined that the correlation degree between factor D and the target parameter is higher than the correlation degree between factor C and the target parameter.

[0090] Optionally, in an embodiment of the present application, the preset sorting conditions may include but are not limited to sorting the pricing factors in the above-mentioned group of pricing factors according to the correlation coefficient values ​​from large to small, and determining the correlation coefficients corresponding to the first three pricing factors as the correlation coefficients that satisfy the preset sorting conditions. At this time, it may include but is not limited to determining these three pricing factors as the above-mentioned second pricing factors, as the pricing factors in the above-mentioned target pricing factors, and then performing regression analysis modeling on the target pricing factors and the target parameters to obtain a three-factor pricing model. By adjusting the target pricing factors to update the three-factor pricing model, the purpose of real-time updating and dynamic adjustment of the three-factor pricing model is achieved.

[0091] As an optional scheme, the above-mentioned determination of the trend data of the target object based on whether the above-mentioned target prediction data meets the basic analysis conditions includes: determining the change dependency relationship between the above-mentioned target parameters and the target supply and demand parameters in the above-mentioned historical data, wherein the above-mentioned basic analysis conditions include the above-mentioned change dependency relationship, and the above-mentioned target supply and demand parameters include the predicted supply parameters and predicted demand parameters in the above-mentioned target prediction data; determining the future supply and demand parameters corresponding to the above-mentioned target supply and demand parameters according to the above-mentioned target prediction data; and determining the above-mentioned trend data based on the above-mentioned future supply and demand parameters and the above-mentioned change dependency relationship.

[0092] Optionally, in an embodiment of the present application, the above-mentioned change dependency relationship may include but is not limited to being determined by performing a correlation analysis on the target parameters and the target supply and demand parameters. The target supply and demand parameters can be used to represent the supply and demand of the target object predicted in the future time period. The supply of the target object here is expressed as, for example, there are 100 target objects obtained through the target supply and demand parameters, while the user only needs 90 target objects. Correspondingly, the above-mentioned change dependency relationship is expressed as, when the supply of the target object is greater than the demand, the value of the target parameter decreases.

[0093] Similarly, the above-mentioned future supply and demand parameters can be used to represent the supply and demand of the target object predicted from various channels in the future period, for example, the supply and demand of the target object predicted by website A. Furthermore, trend data can be determined through future supply and demand parameters and basic analysis conditions.

[0094] It should be noted that there is a basic condition in the above basic analysis conditions that represents the change dependency. For example, condition A in the basic analysis conditions means that when the supply of the target object is greater than the demand, the value of the target parameter decreases, and condition B means that when the supply of the target object is less than the demand, the value of the target parameter increases.

[0095] As an optional scheme, the above-mentioned determination of the change dependency relationship between the above-mentioned target parameters and the target supply and demand parameters in the above-mentioned historical data includes: obtaining the above-mentioned target parameters, supply parameters and demand parameters of at least two adjacent historical time periods in the above-mentioned historical data, wherein the above-mentioned target supply and demand parameters include the above-mentioned supply parameters and the above-mentioned demand parameters; when the supply parameters corresponding to the above-mentioned at least two adjacent historical time periods are greater than the above-mentioned demand parameters, determining the above-mentioned change dependency relationship indicates that the above-mentioned target parameters show a downward trend in the above-mentioned future time period; when the supply parameters corresponding to the above-mentioned at least two adjacent historical time periods are less than the above-mentioned demand parameters, determining the above-mentioned change dependency relationship indicates that the above-mentioned target parameters show an upward trend in the above-mentioned future time period.

[0096] In an exemplary embodiment, assuming that the target object is gold and the target parameter is the gold price, then the supply parameter may represent the supply of gold, the demand parameter may represent the demand for gold, and the target supply and demand parameters may include the supply and demand of gold. Assuming that there are periods A and B in the historical period, and period A is adjacent to period B, for example, period A is January and period B is February. Further, assuming that the gold price in period A is higher than the gold price in period B, the target parameter indicates a decreasing change relationship, and the supply of gold in periods A and B is greater than the demand. Then, the change dependency relationship may be understood as that the gold price falls when the supply parameter is greater than the demand parameter.

[0097] In another exemplary embodiment, it is still assumed that the target object is gold, and the target parameter is the gold price. It is assumed that the gold price in period A is lower than the gold price in period B, indicating that the above target parameter indicates an increasing change relationship, and the supply of gold in period A and period B is less than the demand. Then, the above change dependency relationship can be understood as that the gold price rises when the supply parameter is less than the demand parameter.

[0098] As an optional scheme, the above-mentioned determination of the target critical value of the above-mentioned target parameter in the above-mentioned future time period based on historical data includes: determining the lowest value, the highest value and the target golden section value of the above-mentioned target parameter in the above-mentioned historical time period based on the above-mentioned historical data; determining the change trend of the above-mentioned target parameter in the above-mentioned intermediate time period based on the above-mentioned target golden section value; determining the above-mentioned target critical value based on the above-mentioned change trend, the above-mentioned lowest value or the above-mentioned highest value and the periodic floating ratio of the above-mentioned target parameter.

[0099] Exemplarily, assuming that the target object is gold and the target parameter is the gold price, the above-mentioned minimum value can be understood as the lowest price of gold in the historical period, and the above-mentioned maximum value can be understood as the highest price of gold in the historical period. The above-mentioned target golden section value can be flexibly set artificially, including but not limited to: the golden section point can represent the price point where the gold price turns from falling to rising in the historical period, or the price point where the gold price turns from rising to falling.

[0100] Furthermore, the trend of gold price changes in the middle period can be determined based on the golden section point. For example, the golden section point is Figure 3 The gold price point corresponding to the percentage of 0.618 shown in the figure, at this time, the value of 0.5*0.618 can be taken as 0.191 to determine the periodic floating ratio of gold to be 19.10%. At this time, the target critical point can be determined by the following formula:

[0101] The target critical point value = (1 + periodic floating ratio) * maximum value.

[0102] As an optional solution, the above-mentioned determination of the minimum value, maximum value and target golden section value of the above-mentioned target parameter in the above-mentioned historical period according to the above-mentioned historical data includes: drawing a technical analysis chart according to the above-mentioned historical data, wherein the above-mentioned technical analysis chart includes a target broken line, and the above-mentioned target broken line is used to indicate the change of the above-mentioned target parameter in the above-mentioned historical data according to a preset period; determining the above-mentioned minimum value, the above-mentioned maximum value and the above-mentioned target golden section value based on the above-mentioned target broken line, wherein the above-mentioned target golden section value represents the value corresponding to the above-mentioned target parameter indicated by the golden section point of the target interval with the above-mentioned minimum value as the lower limit and the above-mentioned maximum value as the upper limit; the above-mentioned determination of the change trend of the above-mentioned target parameter in the above-mentioned intermediate period according to the above-mentioned target golden section value includes: obtaining the above-mentioned target parameter of N time periods after the target time period corresponding to the above-mentioned target golden section point; The value corresponding to the target parameter, wherein N is a positive integer; when the value corresponding to the target parameter in N time periods after the target time period is greater than or equal to the target golden section value, the change trend is determined to be increasing; when the value corresponding to the target parameter in N time periods after the target time period is less than the target golden section value, the change trend is determined to be decreasing; the target critical value is determined according to the change trend, the minimum value or the maximum value and the periodic floating ratio of the target parameter, including: when the change trend indicates an increase, the maximum value indicated by the target critical value is determined according to the maximum value and the periodic floating ratio; or, when the change trend indicates a decrease, the minimum value indicated by the target critical value is determined according to the minimum value and the periodic floating ratio.

[0103] In an exemplary embodiment, the above technical analysis chart can be as follows Figure 3 As shown, including the target polyline 302, the target polyline 302 represents the value change of the target parameter in the historical data. The above preset period can be understood as the period in which the target parameter value becomes larger in the historical period, and the period in which the target parameter value becomes smaller in the historical period, such as Figure 3 As shown, the value 1175 of point 304 in the target polyline 302 is the lowest value of the target parameter, the value 1769 of point 306 in the target polyline 302 is the highest value of the target parameter, and the above-mentioned target golden section value is 1430.

[0104] For example, after obtaining the target golden section point, the target period corresponding to the target golden section point can be further determined according to the target broken line in the technical analysis chart, for example Figure 3The 10th month to the 13th month shown are the N time periods mentioned above, where N is 4. In this time period, each time point corresponds to a value of a target parameter. Furthermore, when one or more values ​​of the multiple target parameters corresponding to the N time periods are greater than the golden section value, the value of the target parameter predicted in the future time period will increase, and the periodic floating ratio will be a positive number. At this time, the target critical point can be determined by the following formula:

[0105] Target critical point value = (1 + periodic floating ratio) * maximum value;

[0106] Alternatively, when one or more of the values ​​of the multiple target parameters corresponding to the above N time periods are less than the golden section value, the value of the target parameter predicted in the future time period will become smaller, and the periodic floating ratio will be negative. At this time, the target critical point can be determined by the following formula:

[0107] The target critical point value = (1 + periodic floating ratio) * minimum value.

[0108] The above is only an example, and this application does not make any specific limitation.

[0109] Obviously, the embodiments described above are only part of the embodiments of the present application, rather than all the embodiments.

[0110] The present application is described in detail below with reference to specific embodiments:

[0111] Exemplarily, the embodiments of the present application can be applied to the application scenario of gold price prediction, including but not limited to expanding the data source, including but not limited to macroeconomic indicators, market sentiment, investor preferences, etc., to provide a more comprehensive prediction; dynamically adjust the three-factor pricing model so that the model can adapt to the continuous changes in the market; update in real time to reflect the latest changes in the market, provide a variety of prediction results, reflect the different factors that may affect the gold price, so as to provide a more accurate and comprehensive gold price prediction, and help investors make more informed decisions.

[0112] It should be noted that the above three-factor pricing model can be determined by, but not limited to, the following steps: first, obtaining data, collecting data related to gold prices from multiple channels, including but not limited to historical gold prices, trading volumes, market supply and demand data, virtual currency trends, etc. Compared with related technologies, this application pays more attention to the comprehensiveness and real-time nature of data; data capture, including but not limited to using automated tools (e.g., web crawlers) to capture data from websites, financial data platforms, etc., to ensure the accuracy and real-time nature of the data; data preprocessing, including but not limited to data cleaning: removing duplicate, erroneous or incomplete data to ensure the accuracy and consistency of the data; data conversion: converting raw data into a format suitable for analysis, such as time series data, structured data, etc.; feature engineering: extracting and constructing pricing factors related to gold price prediction based on business knowledge and data analysis; quantitative analysis, selecting a suitable quantitative analysis model, including but not limited to a three-factor pricing model, a machine learning model, etc., which can predict the trend of gold price changes based on historical data and market dynamics; model training: using preprocessed data for model training. During the training process, the model parameters are adjusted to optimize the prediction effect; model verification, using the validation set to verify the model and evaluate the model's predictive performance and generalization ability; the model is updated and dynamically adjusted in real time, and new data is continuously detected to ensure that the model can capture the latest market trends; the model is regularly updated with new data to maintain the model's prediction accuracy and adaptability; according to market changes and the model's prediction effect, the model's parameters or structure are dynamically adjusted to improve the accuracy of the prediction; the three-factor pricing model generates prediction results for the future trend of gold prices, including but not limited to the predicted gold price change range over a period of time, trend analysis, etc., to achieve the purpose of improving the accuracy of gold price prediction. At the same time, by updating and dynamically adjusting the model in real time, it is ensured that the model can adapt to market changes and maintain a high prediction performance.

[0113] For example, technical analysis, fundamental analysis, and three-factor pricing model prediction can be performed on gold prices, respectively. Technical analysis can be used to predict the price trend, trading volume, and market sentiment of gold prices, including but not limited to identifying price trends and trading signals through tools such as charts and indicators; fundamental analysis can be used to determine factors such as macroeconomic factors and virtual currencies that have a long-term impact on gold prices. The three-factor pricing model provides data modeling analysis, technical analysis provides short-term price dynamic information, and fundamental analysis provides long-term trends and influencing factors. In order to form a more accurate prediction, the accuracy and adaptability of gold price prediction can be improved by combining quantitative analysis, real-time model updates, and dynamic adjustments.

[0114] For example, first, the trend of gold price changes in future periods can be predicted based on, but not limited to, the commodity attributes, currency attributes, and financial attributes of gold; then, Figure 3 As shown, according to the wave theory, it can be considered that gold is in an upward trend. The double bottom pattern appears on the target line from the 10th to the 13th month. According to the golden section point, if the support point of 0.618 (1430) is broken in the future, it means that it may enter the next wave of bullish trend. The technical level predicts that the maximum critical value of the gold price in the future period will be around 1846 (the gold price high point will be 0.191 higher). The three-factor pricing model can also be used to predict the gold price to obtain the predicted range of gold prices in the future period.

[0115] Exemplarily, the macroeconomic indicators in the target data can be used for fundamental analysis, and can also be used for quantitative analysis through the three-factor pricing model. In the quantitative analysis, correlation analysis will be first performed between various indicators and gold prices, and parameters with higher correlation will be selected for regression analysis. In addition, the target data can also include sentiment index data for reflecting customers' willingness to buy gold, used to predict short-term gold price fluctuations, and preference index data of gold investors. Model parameters are adjusted based on preference index data to make the three-factor pricing model more in line with the actual market situation. Macroeconomic indicators, sentiment index data, and preference index data can be used for real-time updating and dynamic adjustment of the model. For example, if macroeconomic indicators have changed significantly, the model may need to adjust model parameters according to these new macroeconomic indicators. Through the embodiments of the present application, more details that affect gold price changes can be captured to improve the accuracy of prediction results and help investors more comprehensively. understand the changes in gold prices; and the three-factor pricing model can adapt to the continuous changes in the market. The three-factor pricing model can continuously learn new market behaviors and data patterns, thereby maintaining the timeliness and effectiveness of the model's prediction capabilities, making the gold price prediction method more robust in the face of market fluctuations and able to provide better prediction services. In addition, the embodiment of the present application can predict the time interval of gold prices as needed, for example, once a year. When predicting the gold price, a correlation analysis is periodically performed on the target data and the gold price, and a target pricing factor with a higher correlation is selected for regression analysis. The target pricing factor for implementing the correlation analysis can also be obtained, including but not limited to, using plug-ins.

[0116] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk), and includes a number of instructions for enabling a front-end device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application. The information collected in the above embodiments is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. The above embodiments are based on big data analysis of personal information, and / or use artificial intelligence technology to make automated decisions to make decisions that have a significant impact on personal rights and interests. The technical solution will provide users with corresponding operation entrances for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0117] According to another aspect of the embodiments of the present application, a system access device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0118] Figure 5 is a structural block diagram of a parameter determination device according to an embodiment of the present application, such as Figure 5 As shown, the device comprises:

[0119] A first acquisition module 502 is used to acquire operation data of a target account in a target application, and determine a parameter prediction request according to the operation data, wherein the parameter prediction request matches a parameter type associated with the operation data;

[0120] A second acquisition module 504 is used to acquire target prediction data in response to the parameter prediction request, wherein the target prediction data includes basic data obtained by predicting a future period;

[0121] A first determination module 506 is used to determine the trend data of the target object according to whether the target prediction data meets the basic analysis conditions, wherein the trend data is used to indicate the change trend of the target parameter of the target object in the future period, and the basic analysis conditions are determined by the historical data of the target object in the historical period;

[0122] A second determination module 508 is used to determine a target critical value of the target parameter in an intermediate period of the future period according to the historical data, wherein the target critical value represents a maximum value or a minimum value of the target parameter in the intermediate period;

[0123] The third determination module 510 is used to input the target pricing factor in the target prediction data into the three-factor pricing model to obtain the change range of the target parameter in the future time, wherein the three-factor pricing model is determined by performing regression analysis modeling on the target pricing factor, and the target pricing factor is determined by performing correlation analysis on a set of pricing factors in the historical data and the target parameter;

[0124] A first generating module 512 is used to generate a target prediction result based on the trend data, the target critical value and the change interval, wherein the target prediction result includes a target parameter obtained by predicting a future period;

[0125] The second generating module 514 is used to generate a prompt message associated with the target parameter based on the target prediction result, wherein the prompt message is used to prompt the target account of the state of the target parameter in the target application.

[0126] As an optional scheme, the above-mentioned device is also used for: inputting the target pricing factor in the above-mentioned target prediction data into the three-factor pricing model to obtain the change interval of the above-mentioned target parameter in the above-mentioned future time, performing correlation analysis on the above-mentioned set of pricing factors according to the above-mentioned historical data, and determining a first set of correlation coefficients; determining a first pricing factor according to the above-mentioned first set of correlation coefficients, wherein the correlation coefficient corresponding to the above-mentioned first pricing factor is the correlation coefficient in the above-mentioned first set of correlation coefficients that meets a preset sorting condition, and the above-mentioned target pricing factor includes the above-mentioned first pricing factor; performing regression analysis modeling on the above-mentioned first pricing factor to determine the above-mentioned three-factor pricing model.

[0127] As an optional solution, the above-mentioned device is also used to: update the above-mentioned historical data periodically or at a preset time point; in response to the update of the above-mentioned historical data, re-perform correlation analysis on the above-mentioned set of pricing factors according to the updated historical data to determine a second set of correlation coefficients; determine the second pricing factor according to the above-mentioned second set of correlation coefficients, wherein the correlation coefficient corresponding to the above-mentioned second pricing factor is the correlation coefficient in the above-mentioned second set of correlation coefficients that meets the above-mentioned preset sorting condition, and the above-mentioned target pricing factor includes the above-mentioned second pricing factor; perform regression analysis modeling on the above-mentioned second pricing factor, and update the above-mentioned three-factor pricing model.

[0128] As an optional scheme, the above-mentioned device is used to determine the trend data of the target object according to whether the above-mentioned target prediction data meets the basic analysis conditions in the following manner: determine the change dependency relationship between the above-mentioned target parameters and the target supply and demand parameters in the above-mentioned historical data, wherein the above-mentioned basic analysis conditions include the above-mentioned change dependency relationship; determine the future supply and demand parameters corresponding to the above-mentioned target supply and demand parameters according to the above-mentioned target prediction data; determine the above-mentioned trend data based on the above-mentioned future supply and demand parameters and the above-mentioned change dependency relationship.

[0129] As an optional scheme, the above-mentioned device is used to determine the change dependency relationship between the above-mentioned target parameters and the target supply and demand parameters in the above-mentioned historical data in the following manner: obtain the above-mentioned target parameters, supply parameters and demand parameters of at least two adjacent historical time periods in the above-mentioned historical data, wherein the above-mentioned target supply and demand parameters include the above-mentioned supply parameters and the above-mentioned demand parameters; when the supply parameters corresponding to the above-mentioned at least two adjacent historical time periods are greater than the above-mentioned demand parameters, determining that the above-mentioned change dependency relationship indicates that the above-mentioned target parameters show a downward trend in the above-mentioned future time period; when the supply parameters corresponding to the above-mentioned at least two adjacent historical time periods are less than the above-mentioned demand parameters, determining that the above-mentioned change dependency relationship indicates that the above-mentioned target parameters show an upward trend in the above-mentioned future time period.

[0130] As an optional scheme, the above-mentioned device is used to determine the target critical value of the above-mentioned target parameter in the above-mentioned future time period according to historical data in the following manner: determine the lowest value, the highest value and the target golden section value of the above-mentioned target parameter in the above-mentioned historical time period according to the above-mentioned historical data; determine the change trend of the above-mentioned target parameter in the above-mentioned intermediate time period according to the above-mentioned target golden section value; determine the above-mentioned target critical value according to the above-mentioned change trend, the above-mentioned lowest value or the above-mentioned highest value and the periodic floating ratio of the above-mentioned target parameter.

[0131] As an optional solution, the above-mentioned device is used to determine the minimum value, maximum value and target golden section value of the above-mentioned target parameter in the above-mentioned historical period according to the above-mentioned historical data in the following manner: draw a technical analysis chart according to the above-mentioned historical data, wherein the above-mentioned technical analysis chart includes a target broken line, and the above-mentioned target broken line is used to indicate the change of the above-mentioned target parameter in the above-mentioned historical data according to a preset period; determine the above-mentioned minimum value, the above-mentioned maximum value and the above-mentioned target golden section value based on the above-mentioned target broken line, wherein the above-mentioned target golden section value represents the value corresponding to the above-mentioned target parameter indicated by the golden section point of the target interval with the above-mentioned minimum value as the lower limit and the above-mentioned maximum value as the upper limit; the above-mentioned device is used to determine the change trend of the above-mentioned target parameter in the above-mentioned intermediate period according to the above-mentioned target golden section value in the following manner: obtain N time periods after the target time period corresponding to the above-mentioned target golden section point The value corresponding to the above-mentioned target parameter, wherein N is a positive integer; when the value corresponding to the above-mentioned target parameter in N time periods after the above-mentioned target time period is greater than or equal to the above-mentioned target golden section value, the above-mentioned change trend is determined to be increasing; when the value corresponding to the above-mentioned target parameter in N time periods after the above-mentioned target time period is less than the above-mentioned target golden section value, the above-mentioned change trend is determined to be decreasing; the above-mentioned device is used to determine the above-mentioned target critical value according to the above-mentioned change trend, the above-mentioned minimum value or the above-mentioned maximum value and the periodic floating ratio of the above-mentioned target parameter in the following manner: when the above-mentioned change trend indicates an increase, the maximum value indicated by the above-mentioned target critical value is determined according to the above-mentioned maximum value and the above-mentioned periodic floating ratio; or, when the above-mentioned change trend indicates a decrease, the minimum value indicated by the above-mentioned target critical value is determined according to the above-mentioned minimum value and the above-mentioned periodic floating ratio.

[0132] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0133] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0134] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0135] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0136] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0137] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0138] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0139] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0140] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a parameter, characterized in that: include: Acquire operation data of the target account in the target application, and determine a parameter prediction request according to the operation data, wherein the parameter prediction request matches a parameter type associated with the operation data; In response to the parameter prediction request, obtaining target prediction data, wherein the target prediction data includes basic data predicted for a future period; Determine the trend data of the target object according to whether the target prediction data meets the basic analysis condition, wherein the trend data is used to indicate the change trend of the target parameter of the target object in the future period, and the basic analysis condition is determined by the historical data of the target object in the historical period; Determine, based on the historical data, a target critical value of the target parameter in an intermediate period of the future period, wherein the target critical value represents a maximum value or a minimum value of the target parameter in the intermediate period; Input the target pricing factor in the target forecast data into a three-factor pricing model to obtain the change range of the target parameter in the future time, wherein the three-factor pricing model is determined by performing regression analysis modeling on the target pricing factor, and the target pricing factor is determined by performing correlation analysis on a set of pricing factors in the historical data and the target parameter; Generate a target prediction result based on the trend data, the target critical value and the change interval, wherein the target prediction result includes the target parameter obtained by predicting the future time period; A prompt message associated with the target parameter is generated based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application.

2. The method according to claim 1, characterized in that Before inputting the target pricing factor in the target forecast data into the three-factor pricing model to obtain the change interval of the target parameter in the future time, the method further includes: Performing a correlation analysis on the set of pricing factors according to the historical data to determine a first set of correlation coefficients; Determining a first pricing factor according to the first group of correlation coefficients, wherein the correlation coefficient corresponding to the first pricing factor is a correlation coefficient in the first group of correlation coefficients that satisfies a preset sorting condition, and the target pricing factor includes the first pricing factor; Perform regression analysis modeling on the first pricing factor to determine the three-factor pricing model.

3. The method according to claim 2, characterized in that The method further comprises: Update the historical data periodically or at a preset time point; In response to the historical data being updated, re-analyzing the correlation of the set of pricing factors according to the updated historical data to determine a second set of correlation coefficients; determining a second pricing factor according to the second group of correlation coefficients, wherein the correlation coefficient corresponding to the second pricing factor is a correlation coefficient in the second group of correlation coefficients that satisfies the preset sorting condition, and the target pricing factor includes the second pricing factor; Perform regression analysis modeling on the second pricing factor to update the three-factor pricing model.

4. The method according to claim 1, characterized in that: The determining of the trend data of the target object according to whether the target prediction data meets the basic analysis conditions includes: Determining a change dependency relationship between the target parameter and the target supply and demand parameter in the historical data, wherein the basic analysis condition includes the change dependency relationship; Determining future supply and demand parameters corresponding to the target supply and demand parameters according to the target forecast data; The trend data is determined based on the future supply and demand parameters and the change dependency.

5. The method according to claim 4, characterized in that The determining of the change dependency relationship between the target parameter in the historical data and the target supply and demand parameter includes: Acquire the target parameter, supply parameter and demand parameter of at least two adjacent historical periods in the historical data, wherein the target supply and demand parameter includes the supply parameter and the demand parameter; In a case where the supply parameter corresponding to the at least two adjacent historical time periods is greater than the demand parameter, determining that the change dependency relationship indicates that the target parameter has a downward trend in the future time period; In the case where the supply parameter corresponding to the at least two adjacent historical time periods is less than the demand parameter, determining the change dependency relationship indicates that the target parameter has an upward trend in the future time period.

6. The method according to claim 1, characterized in that Determining the target critical value of the target parameter in the future period according to historical data includes: Determine the lowest value, the highest value and the target golden section value of the target parameter in the historical period according to the historical data; Determine the change trend of the target parameter in the intermediate period according to the target golden section value; The target critical value is determined according to the change trend, the minimum value or the maximum value and the periodic floating ratio of the target parameter.

7. The method according to claim 6, characterized in that The determining, according to the historical data, the lowest value, the highest value, and the target golden section value of the target parameter in the historical period, comprises: drawing a technical analysis chart according to the historical data, wherein the technical analysis chart comprises a target broken line, and the target broken line is used to indicate the change of the target parameter in the historical data according to a preset period; determining the lowest value, the highest value, and the target golden section value based on the target broken line, wherein the target golden section value represents the value corresponding to the target parameter indicated by the golden section point of the target interval with the lowest value as the lower limit and the highest value as the upper limit; Determining the change trend of the target parameter in the intermediate period according to the target golden section value includes: obtaining values ​​corresponding to the target parameter in N periods after the target period corresponding to the target golden section point, where N is a positive integer; when the values ​​corresponding to the target parameter in the N periods after the target period are greater than or equal to the target golden section value, determining that the change trend is increasing; when the values ​​corresponding to the target parameter in the N periods after the target period are less than the target golden section value, determining that the change trend is decreasing; The method of determining the target critical value based on the changing trend, the minimum value or the maximum value and the periodic floating ratio of the target parameter includes: when the changing trend indicates an increase, determining the maximum value indicated by the target critical value based on the maximum value and the periodic floating ratio; or, when the changing trend indicates a decrease, determining the minimum value indicated by the target critical value based on the minimum value and the periodic floating ratio.

8. A parameter determination device, characterized in that: include: A first acquisition module, configured to acquire operation data of a target account in a target application, and determine a parameter prediction request according to the operation data, wherein the parameter prediction request matches a parameter type associated with the operation data; A second acquisition module, configured to acquire target prediction data in response to the parameter prediction request, wherein the target prediction data includes basic data obtained by predicting a future period; A first determination module is used to determine the trend data of the target object according to whether the target prediction data meets the basic analysis conditions, wherein the trend data is used to indicate the change trend of the target parameter of the target object in the future period, and the basic analysis conditions are determined by the historical data of the target object in the historical period; A second determination module is used to determine a target critical value of the target parameter in the middle period of the future period according to the historical data, wherein the target critical value represents the maximum value or the minimum value of the target parameter in the middle period; A third determination module is used to input the target pricing factor in the target prediction data into a three-factor pricing model to obtain a variation range of the target parameter in the future time, wherein the three-factor pricing model is determined by performing regression analysis modeling on the target pricing factor, and the target pricing factor is determined by performing correlation analysis on a set of pricing factors in the historical data and the target parameter; A first generating module, configured to generate a target prediction result based on the trend data, the target critical value and the change interval, wherein the target prediction result includes the target parameter obtained by predicting the future period; The second generating module is used to generate a prompt message associated with the target parameter based on the target prediction result, wherein the prompt message is used to prompt the target account of the status of the target parameter in the target application.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

Images