Investment model updating method and device, equipment, medium and program product

Abstract

The invention discloses an investment model updating method and device, equipment, a medium and a program product. Comprising the steps that if it is detected that at least one kind of industry associated data is updated, target associated data in an updated state is acquired; wherein the industry association data is at least associated with a specified industry; determining at least one type of target index data associated with the target associated data; wherein the target index data is associated with the income state of the specified industry in at least one time period; and if the at least one type of target index data meets a model updating condition, updating an investment model associated with the specified industry based on the target associated data and / or the target index data.

Description

Technical Field

[0001] The present application relates to the field of investment technology, and in particular to an investment model updating method, device, equipment, medium and program product. Background Art

[0002] In actual applications, investment researchers usually need to pay attention to the changing status of industry-related data, and after learning about the changes in industry-related data, manually calculate indicators related to the industry-related data, and determine whether to update the investment model based on the above indicators. However, the above method is inefficient and cannot meet the real-time needs of industry investment. Summary of the invention

[0003] Based on the above technical problems, the embodiments of the present application provide an investment model updating method, device, equipment, medium and program product.

[0004] The technical solution provided by the embodiment of the present application is as follows:

[0005] The present application embodiment first provides a method for updating an investment model, the method comprising:

[0006] If at least one industry-related data update is detected, obtaining target-related data in an updated state; wherein the industry-related data is at least associated with a designated industry;

[0007] Determine at least one target indicator data associated with the target-related data; wherein the target indicator data is associated with the revenue status of the specified industry in at least one time period;

[0008] If the at least one target indicator data satisfies the model update condition, the investment model associated with the designated industry is updated based on the target association data and / or the target indicator data.

[0009] In some embodiments, the determining of at least one target indicator data associated with the target-related data includes:

[0010] Determine a dependency graph between industry parameters; wherein the industry parameters are associated with the specified industry; and the industry parameters include the target association data;

[0011] The target-related data is calculated based on the dependency graph to obtain the at least one target indicator data.

[0012] In some embodiments, determining a dependency graph between industry parameters includes:

[0013] Obtaining a set of calculation formulas for characterizing the calculation relationship between the industry parameters;

[0014] The association relationships between the industry parameters associated with the calculation formulas in the calculation formula set are integrated to obtain the dependency graph.

[0015] In some embodiments, the calculating the target-related data based on the dependency graph to obtain the at least one target indicator data includes:

[0016] Determining a calculation order of calculation formulas in a set of calculation formulas associated with the dependency graph;

[0017] Based on the calculation order, at least the target-related data is calculated using a calculation formula in the calculation formula set to obtain the at least one target indicator data.

[0018] In some embodiments, determining the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph includes:

[0019] Analyze the industry parameters in the dependency graph by a topological sorting algorithm to determine the dependency relationship between the industry parameters;

[0020] Based on the dependency and the corresponding relationship, the calculation order is determined; wherein the corresponding relationship includes the corresponding relationship between the industry parameters in the dependency graph and the calculation formulas in the calculation formula set.

[0021] In some embodiments, if the at least one target indicator data satisfies a model update condition, updating the investment model associated with the specified industry based on the target association data and / or the target indicator data includes:

[0022] If the at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a degree threshold, generate and output model update warning information to indicate that the investment model is updated at least based on the target-associated data and / or the target indicator data; wherein the model update condition includes that the at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a preset threshold.

[0023] The embodiment of the present application further provides a device for updating an investment model, the device for updating an investment model comprising:

[0024] An acquisition module, configured to acquire target associated data in an updated state if at least one industry associated data update is detected; wherein the industry associated data is at least associated with a designated industry;

[0025] A determination module, configured to determine at least one target indicator data associated with the target associated data; wherein the target indicator data is associated with the revenue status of the specified industry in at least one time period;

[0026] An updating module is used to update the investment model associated with the specified industry based on the target association data and / or the target indicator data if the at least one target indicator data satisfies the model updating condition.

[0027] An embodiment of the present application also provides an electronic device, which includes a processor and a memory; a computer program is stored in the memory; when the computer program is executed by the processor, it can implement the investment model updating method as described in any of the above.

[0028] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored; when the computer program is executed by a processor of an electronic device, the investment model updating method as described in any of the above can be implemented.

[0029] An embodiment of the present application also provides a computer program product, which includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement any of the investment model updating methods described above.

[0030] In the updating method of the investment model provided in the embodiment of the present application, if at least one industry-related data update is detected, the target-related data in the updated state is obtained, and the industry-related data is at least associated with the specified industry, thereby realizing the automatic monitoring of the industry-related data associated with the specified industry, thereby reducing the inefficiency and the probability of data omission caused by manual monitoring of the industry-related data; and, by determining at least one target indicator data associated with the target-related data, the automation level of the operation of determining the target indicator data is improved, thereby reducing the human cost of the operation of manually determining the target indicator data, and, through the above operation, the correlation between the target-related data and the target indicator data is realized. On the other hand, since the target indicator data is associated with the profit status of the specified industry in at least one time period, the degree of correlation between the target indicator data and the profit status in the time dimension can be improved; on this basis, if at least one indicator data meets the model update conditions, the investment model associated with the specified industry is updated based on the target association data and / or the target indicator data. In this way, not only the automatic update of the investment model is realized, but also the targeted update of the investment model can be improved, thereby improving the accuracy and real-time performance of the updated investment model in predicting the profit status of the specified industry, providing stable data support for industry investment, and thus meeting the real-time requirements of industry investment decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A flowchart of a method for updating an investment model provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of the flow of a topological sorting algorithm provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of a process for updating a profit splitting model provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of a process of warning adjustment of a stock profit splitting model provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of the structure of an updating device for an investment model provided in an embodiment of the present application;

[0036] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0038] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0039] In the industry investment scenario, the research of investment researchers on industry-related stocks mainly includes the research on the profit split model of individual stocks. Among them, the research on the profit split model of individual stocks is based on the prediction of future data. At the same time, as time goes by, various new industry data often appear in various industries, and these new industry data may affect the research logic of the profit split model of individual stocks. Therefore, when new industry data appears, researchers need to adjust the prediction data in time to improve the accuracy of the profit investment model of individual stocks.

[0040] For example, investment researchers usually summarize industry data through software tools including spreadsheet tools set up in local computer devices, and analyze the summarized industry data through cell formulas in the spreadsheet tools to determine the cross-reference relationship between industry-related parameters or indicator data; for example, by constructing cell formulas, researchers can split important indicator data such as the industry's operating income and operating costs into underlying product data, and then use the profit splitting model to predict and process the product data to infer operating income and cost data in future time periods.

[0041] Therefore, once new industry data emerges in an industry or market, researchers are required to manually determine whether these new industry data will affect the original profit split model. If it is determined that these new industry data will affect the original profit split model, the profit split model needs to be readjusted based on these new industry data.

[0042] Obviously, the updating scheme of the profit split model by the related technology has at least the following disadvantages: first, the researchers cannot track the diversified industry data in real time, and when the industry data is updated, the researchers cannot manually compare all the individual stock profit models one by one to see if they are affected. Therefore, the labor cost of the above scheme is too high and the accuracy is insufficient; moreover, the industry data concerned in the above scheme are relatively basic, and the correlation between these basic industry data and the actual individual stock profit model is not obvious enough. Therefore, the derivative factors between the basic industry data and the actual individual stock profit model also need to be manually determined by the researchers. Therefore, the labor cost of the above scheme has been further increased; at the same time, the original industry data monitoring is also achieved with the help of manpower, which may lead to omissions in the monitoring results of the industry data, and it is impossible to remind the researchers to update the individual stock investment model.

[0043] Based on the above technical problems, the embodiments of the present application provide an investment model updating method, device, equipment, medium and program product.

[0044] The embodiment of the present application first provides a method for updating an investment model. Figure 1 A flow chart of a method for updating an investment model provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method may include the following steps:

[0045] Step 101: If at least one industry-related data update is detected, obtain target-related data in an updated state.

[0046] Among them, industry-related data is at least related to a designated industry.

[0047] Accordingly, if at least one industry-related data update is not detected, the target-related data may not be acquired.

[0048] In one embodiment, the designated industry may include at least one predetermined industry; illustratively, the industry may include agriculture, forestry, animal husbandry and fishery, construction and building materials, metallurgy and mining, petrochemicals, water conservancy and hydropower, transportation, information industry, machinery and electronics, light industry and food, tourism and leisure, environmental protection and greening, and office culture and education, etc.

[0049] In one embodiment, the industry-related data may include data directly related to a specified industry; illustratively, the industry-related data may include deposit interest rates and loan interest rates related to the financial industry, and may also include birth rates and death rates related to population structure.

[0050] In one implementation, the industry-related data may include basic industry data directly related to a designated industry.

[0051] In one implementation, based on the data type, industry-related data may be divided into macroeconomic data, status data related to the industry development status, data on the industry chain in which the industry is located, and data related to companies or organizations in the industry.

[0052] In one implementation, based on the data source, the industry-related data may be divided into external interface data, website analysis data, and corporate annual report analysis data.

[0053] In one implementation, industry-related data may be divided into structured data and unstructured data according to the structure of the data.

[0054] In one implementation, the target-related data may include industry-related data whose value has changed. For example, if the value of a deposit interest rate is updated from a first interest rate to a second interest rate, the target-related data may include the deposit interest rate.

[0055] In one implementation, the target-related data may include newly-emerged industry-related data, and may also include industry-related data that existed in the past but has been switched to an invalid state.

[0056] In one embodiment, a data set associated with a specified industry may be monitored in real time or at specified time intervals through a pre-set data monitoring module to detect whether at least one industry-related data is updated.

[0057] Step 102: Determine at least one target indicator data associated with the target-related data.

[0058] Among them, the target indicator data is associated with the revenue status of a specified industry in at least one time period.

[0059] In one embodiment, the target indicator data may be directly or indirectly associated with the target associated data.

[0060] In one embodiment, the target-related data may include data directly related to the specified industry, while the target indicator data may be indirectly related to the specified industry; illustratively, the target indicator data may be at least one of the derived indicator data of the specified industry.

[0061] In one implementation, the target indicator data may be directly or indirectly associated with the revenue status, and the target indicator data may include a value of at least one indicator.

[0062] In one embodiment, the profitability status may be determined by analyzing financial indicators of a specified industry.

[0063] In one embodiment, the profit status may include the rate of return or the amount of profit of a specified industry in at least one time period, and may also represent the loss rate or the amount of loss of a specified industry in at least one time period.

[0064] In one implementation, the at least one time period may be based on any one of a week, a month, a quarter, and a year as a basic time unit.

[0065] In one implementation, the target indicator data may be determined by any of the following methods:

[0066] According to the revenue status determination method of the designated industry, the target-related data is calculated, and the intermediate data and result data associated with the above calculation process are integrated to obtain an integrated result, and the integrated result is determined as at least one target indicator data.

[0067] Determine the target income of the designated industry, determine the association relationship between the target income and the target association data, and determine a set of a series of indicator data included in the above association relationship as at least one target indicator data.

[0068] Step 103: If at least one target indicator data satisfies the model update condition, the investment model associated with the specified industry is updated based on the target association data and / or the target indicator data.

[0069] Accordingly, if at least one target indicator data does not satisfy the model update condition, updating the investment model associated with the specified industry based on the target association data and / or the target indicator data may not be performed.

[0070] In one embodiment, the model update condition may include that the value of at least one target indicator data is greater than or equal to a first threshold, and may also include that the number of indicator data in at least one target indicator data is greater than or equal to a second threshold, and may also include that the degree of influence of the indicator data in at least one target indicator data on the profit status is greater than or equal to a third threshold.

[0071] In one embodiment, the investment model may include an individual stock investment model or an individual stock profit split model associated with a specified industry; wherein the individual stock profit split model is mainly used to decompose the operating income, operating costs, gross profit and gross profit margin of the main business of the individual stock, and decompose them into basic products and industry factors through mathematical formulas, so as to determine the impact of the basic products and industry factors on the company's revenue, and by predicting the future data of the basic products and industry factors, the company's future main revenue is calculated to evaluate the company's future development potential.

[0072] In one embodiment, the investment model may be updated in any of the following ways:

[0073] According to the magnitude change of the target associated data and / or the magnitude change of the target indicator data, the first parameter related to the target associated data and / or the target indicator data in the investment model is updated to update the investment model; wherein the first parameter may include a weight parameter and a logical calculation relationship.

[0074] According to the newly added or invalid state of the target associated data, the second parameter associated with the target indicator data in the investment model is updated to update the investment model; wherein the second parameter may include a logical calculation relationship or a mapping relationship.

[0075] For example, when the technical solution provided by the embodiment of the present application is applied to a financial investment scenario, the researcher can pre-build a stock profit split model, and then estimate at least part of the indicator data contained therein. For example, the researcher estimates that the sales volume of product B of company A in 2025 is 100 units, and the researcher believes that the sales volume is related to the pre-set industry indicator C, which is calculated based on the bank interest rate r and cannot be directly seen through the data. In this case, the researcher can use the industry calculator to construct the relationship between the industry indicator C and the bank interest rate r as shown in formula (1):

[0076] C=f(r) (1)

[0077] From formula (1), it can be seen that if the bank interest rate is updated, the industry indicator C will be updated synchronously. Therefore, in order to trigger the adjustment of the profit model of Company A by monitoring the changes in C, a monitoring mechanism can be set to monitor C. For example, if C is greater than a certain value s, it triggers the update of the individual stock profit split model.

[0078] For example, if the bank interest rate indicator r is updated on a certain day, C can be automatically calculated, and when the updated industry indicator C is greater than s, the update of the individual stock profit split model is triggered to improve the consistency between the individual stock profit split model and the bank interest rate.

[0079] In the above example, the target associated data may be the bank interest rate r, and the target indicator data may be the industry indicator C.

[0080] Among them, the industry calculator enables researchers to build workflows between industry indicator data based on existing industry indicator data, thereby obtaining derivative industry indicators that meet research needs. These industry derivative indicators can become the data basis for updating investment models.

[0081] As can be seen from the above, in the updating method of the investment model provided by the embodiment of the present application, if at least one industry-related data update is detected, the target-related data in the updated state is obtained, and the industry-related data is at least associated with the specified industry, thereby realizing the automatic monitoring of the industry-related data associated with the specified industry, thereby reducing the inefficiency and the probability of data omission caused by manual monitoring of the industry-related data; and, by determining at least one target indicator data associated with the target-related data, the automation level of the operation of determining the target indicator data is improved, thereby reducing the human cost of the operation of manually determining the target indicator data, and, through the above operation, the target-related data and the target indicator data are realized. On the other hand, since the target indicator data is associated with the profit status of the specified industry in at least one time period, the degree of correlation between the target indicator data and the profit status in the time dimension can be improved; on this basis, if at least one indicator data meets the model update conditions, the investment model associated with the specified industry is updated based on the target associated data and / or the target indicator data. In this way, not only the automatic update of the investment model is realized, but also the targeted update of the investment model can be improved, thereby improving the accuracy and real-time performance of the updated investment model in predicting the profit status of the specified industry, providing stable data support for industry investment, and thus meeting the real-time requirements of industry investment decisions.

[0082] Based on the foregoing embodiment, in the method for updating the investment model provided in the embodiment of the present application, determining at least one target indicator data associated with the target associated data can be achieved by the following steps:

[0083] Step A1: Determine the dependency graph between industry parameters.

[0084] Among them, the industry parameter is associated with the specified industry; the industry parameter includes target-related data.

[0085] In one embodiment, the industry parameters may include a set of parameters that can characterize the development, revenue, and scale changes of a specified industry.

[0086] In one implementation, the industry parameters may include basic industry parameters of a specified industry, and may also include parameters directly or indirectly associated with the basic industry parameters.

[0087] In one embodiment, the dependency graph may include the mutual dependencies between parameters in the industry parameters, and may also include the order of appearance of the kth parameter and the k+1th parameter in the industry parameters; wherein k may be an integer greater than or equal to 1.

[0088] In one embodiment, the dependency graph may be determined by:

[0089] The calculation relationship between industry parameters that can characterize the development status and / or development law of a specified industry in at least one dimension is sorted out to determine the order in which the parameters in the industry parameters appear in the above calculation relationship, and a dependency relationship map is constructed based on the above order.

[0090] Step A2: Calculate the target association parameters based on the dependency graph to obtain at least one target indicator data.

[0091] In one embodiment, at least one target indicator data may be obtained by:

[0092] The order of priority between the target association parameter and other parameters in the industry parameters is determined from the dependency graph, and then the target association data is calculated according to the above order to obtain at least one target indicator data.

[0093] From the above, it can be seen that in the updating method of the investment model provided in the embodiment of the present application, a dependency graph between industry parameters associated with a specified industry is determined, and the industry parameters include target-related data. In this way, the dependency graph can intuitively, comprehensively and accurately characterize the chronological dependency between industry parameters; and, based on the dependency graph, the target-related data is calculated to obtain at least one target indicator data. In this way, through the above operations, targeted calculation of the target-related data is achieved, thereby improving the calculation efficiency of at least one target indicator data.

[0094] Based on the above embodiment, in the method for updating the investment model provided in the embodiment of the present application, determining the dependency graph between industry parameters can be achieved by the following steps:

[0095] Step B1: Obtain a set of calculation formulas for characterizing the calculation relationship between industry parameters.

[0096] In one implementation, the calculation formula set may be included in an industry calculator for a specified industry.

[0097] In one embodiment, the calculation formulas in the calculation formula set can be embodied in the form of functions; accordingly, the above-mentioned calculation relationship may include the order between the input data and output data of the function, the input data and the first intermediate data required to be based on the function calculation process, and the second intermediate data obtained in the function calculation process and the output data.

[0098] In one implementation, the calculation relationship may also include a calling relationship and / or a called relationship between calculation formulas in the calculation formula set.

[0099] In one implementation, the calculation formula set may be obtained in the following manner:

[0100] A calculation formula set is obtained by integrating all calculation formulas associated with industry calculators associated with a specified industry.

[0101] Step B2: Integrate the associations between the industry parameters associated with the calculation formulas in the calculation formula set to obtain a dependency graph.

[0102] In one implementation, the dependency graph may be obtained by:

[0103] Determine the calling relationship and the called relationship between the calculation formulas in the calculation formula set, sort the calculation formulas in the calculation formula set according to the calling relationship and the called relationship, obtain the formula sorting result, and then determine and construct a dependency graph based on the dependency relationship between the input data of the kth calculation formula, the output data of the kth calculation formula, the input data of the k+1th calculation formula, and the output data of the k+1th calculation formula according to the order of the calculation formulas represented by the formula sorting result; wherein k is a formula greater than or equal to 1 and less than or equal to K-1; K is the number of calculation formulas included in the calculation formula set; wherein the industry parameters may include the input data of the kth calculation formula, the output data of the kth calculation formula, the input data of the k+1th calculation formula, and the output data of the k+1th calculation formula.

[0104] From the above, it can be seen that the updating method of the investment model provided in the embodiment of the present application obtains a set of calculation formulas for characterizing the calculation relationship between industry parameters, and then integrates the association relationship between the industry parameters associated with the calculation formulas in the calculation formula set to obtain a dependency graph. In this way, through the above method, the consistency between the industry parameters in the dependency graph and the industry parameters in the calculation formula set can be improved, and the consistency between the sequence or causal relationship between the industry parameters in the dependency graph and the calculation relationship between the industry parameters in the calculation formula set can be improved, thereby improving the accuracy of the dependency graph.

[0105] Based on the above embodiments, in the method for updating the investment model provided in the embodiments of the present application, the target association data is calculated based on the dependency graph to obtain at least one target indicator data, which can be achieved by the following steps:

[0106] Step C1: determine the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph.

[0107] In one implementation, the calculation order may represent the order of the calculation formulas in the time dimension.

[0108] In one implementation, the calculation order may be determined as follows:

[0109] Based on the mutual dependencies between industry parameters in the dependency graph and the calling relationships between calculation formulas in the calculation formula set, the order of calculating the calculation formulas in the calculation formula set is determined.

[0110] Step C2: Based on the calculation order, at least the target-related data is calculated using a calculation formula in the calculation formula set to obtain at least one target indicator data.

[0111] In one embodiment, at least one target indicator data may be obtained by:

[0112] Based on the calculation order, determine the first formula in the calculation formula set for processing the target-related data, the second formula for calling the first formula, ..., and the Kth formula for calling the K-1th formula, and process the target-related data through the first formula to obtain a first calculation result, and then calculate the first calculation result and other industry parameters that the second formula depends on through the second formula to obtain a second calculation result, ..., to obtain the K-1th calculation result, and finally process at least the K-1th calculation result through the Kth formula to obtain at least one target indicator data.

[0113] In one embodiment, at least one target indicator data may include the calculation result of the Kth formula, and may also include the calculation result of at least one output from the second formula to the K-1th formula.

[0114] As can be seen from the above, in the investment model update method provided by the embodiment of the present application, after determining the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph, at least the target-related data is calculated by the calculation formulas in the calculation formula set based on the calculation order to obtain at least one target indicator. In this way, through the above operation, the probability of data blocking in the calculation process of at least one target indicator data can be reduced, thereby improving the pertinence and calculation efficiency of the calculation process of at least one target indicator data.

[0115] Based on the above embodiments, in the method for updating the investment model provided in the embodiments of the present application, determining the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph can be achieved by the following steps:

[0116] Step D1: Analyze the industry parameters in the dependency graph using a topological sorting algorithm to determine the dependency relationships between the industry parameters.

[0117] In one implementation, the dependency graph may be a directed acyclic graph.

[0118]

[0119] In one embodiment, the industry parameters in the dependency graph are analyzed by a topological sorting algorithm, which can be implemented by the pseudocode shown above; wherein node A can be any industry parameter, and formula formula can be a calculation formula associated with the industry parameter represented by node A contained in an industry calculator corresponding to the specified industry.

[0120] Exemplarily, the core idea of ​​the above pseudo code can be implemented through steps 1 to 3:

[0121] Step 1: Select a node with an in-degree of 0 from the dependency graph and output the node;

[0122] Step 2: Delete the node and its associated arcs from the dependency graph, and adjust the in-degree of the arc head node of the deleted arc, that is, reduce the in-degree by one;

[0123] Step 3: Repeat steps 1 and 2 until all nodes with in-degree 0 are output, or there are no more nodes with in-degree 0 in the dependency graph.

[0124] Figure 2 A schematic diagram of the flow of the topological sorting algorithm provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the process may include the following steps:

[0125] Step 201, start.

[0126] Exemplarily, at step 201 , a dependency graph may be obtained.

[0127] Step 202: Construct the in-degree list in[i] of the dependency adjacency list dependency through the regular matching parsing formula.

[0128] Exemplarily, the in-degree list in[i] of the dependency adjacency list dependency can be associated with the dependency graph.

[0129] Step 203: Build a queue queue, and push the nodes with a value of 0 in the in-degree list into the topological sorting sequence sequence.

[0130] Step 204: Determine whether len(queue) is 0.

[0131] Exemplarily, if len(queue) is not 0, the first branch including steps 205 to 206 may be executed, and if len(queue) is 0, the second branch including steps 207 to 210 may be executed.

[0132] Step 205: queue pops out a node node, and sequence pushes node node.

[0133] Exemplarily, the node popped out of the queue may be the same node as the node pushed into the sequence.

[0134] Step 206: Reduce the in-degree of the node that the node depends on by 1 according to the dependency array. If the in-degree of the node that the node depends on is reduced to 0, it is pushed into the queue.

[0135] Exemplarily, after step 206 is completed, step 204 may be continued to be executed to continuously push nodes with an in-degree of 0 into the queue.

[0136] Step 207: Determine whether len(sequence) is not equal to the number of nodes.

[0137] Exemplarily, the number of nodes may include the number of industry parameters included in the dependency graph.

[0138] Exemplarily, if len(sequence) is not equal to the number of nodes, step 208 may be executed, and if len(sequence) is equal to the number of nodes, step 209 may be executed.

[0139] Step 208: Determine whether a dependency cycle exists.

[0140] Exemplarily, after step 208 is completed, step 210 may be executed.

[0141] Step 209: Obtain the topological sorting result sequence.

[0142] Exemplarily, the topological sorting result may include intuitive dependencies between industry parameters.

[0143] Exemplarily, step 210 may be executed after step 209 is completed.

[0144] Step 210, end.

[0145] Through the above method, the dependency relationships between industry parameters in the dependency graph can be quickly and effectively sorted out.

[0146] Step D2: Determine the calculation order based on the dependency relationship and the corresponding relationship.

[0147] The corresponding relationship includes the corresponding relationship between the industry parameters in the dependency graph and the calculation formulas in the calculation formula set.

[0148] In one implementation, the corresponding relationship may include a corresponding relationship between the industry parameters and the calculation formulas generated due to the calculation or mapping of the industry parameters in the dependency relationship by the calculation formulas in the calculation formula set.

[0149] Exemplarily, after the calculation order is determined, the calculation formula in the calculation formula set can be parsed by the following pseudo code, and the industry parameters inputted therein can be calculated by the calculation formula.

[0150] Exemplarily, in the above pseudo code, the calculation priority may include: left bracket, right bracket, comma is 0, +, - is 1, *, \ is 2, and the number of formula set in the above pseudo code may be 3.

[0151] Through the above pseudo code, accurate parsing of indicators and operators in any calculation formula is achieved; wherein, the above indicators can be the industry parameters in the aforementioned embodiments, and can also include target indicator data.

[0152]

[0153] It should be noted that in the above calculation formula, the ${} symbol can be used to distinguish indicators and constants. The indicator ID is filled in the curly brackets. For example, ${aaa}+${bbb} is used to represent the addition of indicator aaa and indicator bbb.

[0154] From the above, it can be seen that in the updating method of the investment model provided in the embodiment of the present application, the industry parameters in the dependency graph are analyzed by a topological sorting algorithm to determine the dependency between the industry parameters, and the calculation order is determined based on the dependency and the corresponding relationship, and the corresponding relationship includes the corresponding relationship between the industry parameters in the dependency graph and the calculation formula in the calculation formula set. In this way, through the above method, with the help of a topological sorting algorithm, the advantage of sorting out the complex dependency between the industry parameters in the dependency graph can be achieved, which can improve the accuracy and intuitiveness of the dependency, thereby improving the accuracy of the calculation order.

[0155] Based on the foregoing embodiments, in the method for updating the investment model provided in the embodiments of the present application, if at least one target indicator data satisfies the model update condition, updating the investment model associated with the specified industry based on the target association data and / or the target indicator data can also be achieved in the following manner:

[0156] If at least one target indicator data includes indicator data of a target type and the fluctuation degree of the target indicator data is greater than or equal to the degree threshold, a model update warning is generated and output to indicate that the investment model is updated based on at least the target-related data and / or the target indicator data.

[0157] The model update condition includes at least one target indicator data including indicator data of a target type, and the fluctuation degree of the target indicator data is greater than or equal to a preset threshold.

[0158] Accordingly, if at least one target indicator data does not include indicator data of the target type, or the fluctuation degree of the target indicator data is less than the degree threshold, the model update warning may not be generated and output.

[0159] In one embodiment, the target type may be pre-set by the researcher, and the target type may include at least one type.

[0160] In one embodiment, the degree of fluctuation of the target indicator data is greater than or equal to a degree threshold, and may include the absolute value of the difference between the first indicator value and the second indicator value being greater than or equal to the degree threshold; wherein the first indicator value may include the value of the target indicator data corresponding to the investment model, and the second indicator value may include the value of the target indicator data at the current moment determined by the method provided in the aforementioned embodiment.

[0161] In one implementation, the model update condition may also include that the value of the target indicator data is greater than or equal to a first threshold.

[0162] In one implementation, the model update warning information may include a value and / or type of at least one target indicator data.

[0163] In one implementation, the model update warning information may be embodied in at least one form of text, video, and picture.

[0164] In one embodiment, after the model update warning information is generated, it can also be sent to an electronic device associated with the researcher to remind the researcher to update the investment model based on at least the target-related data and / or the target indicator data; exemplarily, the model update warning information can be sent to the electronic device via telephone, social software, email, and text messages; exemplarily, the electronic device can include a smart phone and / or a computer device, etc.

[0165] Figure 3A schematic diagram of the process of updating the profit split model provided in the embodiment of the present application. Figure 3 As shown, the process can be implemented by a data acquisition module 301, Kafka 302, a real-time monitoring module 303, XXL-Job 304, an industry calculator 305, and an early warning module 306. The above process may specifically include the following steps:

[0166] Step 307: Send indicator data.

[0167] Exemplarily, the data acquisition module 301 can acquire basic financial indicator data related to the financial industry in real time, and send the basic financial indicator data to Kafka 302 .

[0168] Exemplarily, the data acquisition module 301 may also send indicator data to Kafka302 when detecting that the basic financial indicator data is updated, and the indicator data may include an indicator identifier of the updated basic financial indicator data to indicate to Kafka302 that the basic financial indicator data indicated by the above identifier has been updated; exemplarily, the indicator identifier may include the number and / or name of the basic financial indicator data.

[0169] Step 308: Send the indicator identifier.

[0170] Exemplarily, after receiving the indicator identifier, Kafka302 can send the indicator identifier to XXL-Job.

[0171] Among them, Kafka is a distributed, high-throughput, and persistent messaging system that processes real-time data streams through Kafka message queues. First, Kafka has the advantages of high throughput and scalability with its distributed architecture. It can store messages on multiple device nodes, and each device node is responsible for processing a part of the messages. This architecture enables Kafka to be expanded on multiple servers to process large amounts of data. Second, Kafka has a high throughput capacity, which enables it to process large amounts of data, but its data processing performance is limited by disk input and output (I / O) and network bandwidth. In order to make up for the above shortcomings, Kafka uses batch processing and partitioning technology to improve data processing. processing performance; at the same time, Kafka stores messages on disk to achieve persistence of message storage, which means that even if the Kafka server crashes, the stored messages will not be lost; on the other hand, Kafka can improve the consistency of messages through the partitioning mechanism. Each partition stores a unique leader copy, and other copies synchronize data from the leader copy. When the leader copy crashes, other copies can become new leader copies, thereby improving the consistency of messages; in addition, Kafka can also expand its processing power by adding more device nodes. This scalability enables Kafka to process more data while maintaining the advantages of high throughput and low latency.

[0172] Step 309: Scheduling tasks.

[0173] Exemplarily, Kafka302 may trigger XXL-Job304 to perform task scheduling, so as to parse the calculation formulas in the calculation formula set contained in the industry calculator through XXL-Job304, thereby obtaining a dependency graph.

[0174] Among them, XXL-Job is an open source distributed task scheduling platform, which is developed based on Java and provides functions such as task distributed scheduling center, task executor and task tracking. Its main purpose is to simplify the complexity of distributed task scheduling and improve task execution efficiency.

[0175] XXL-Job provides a distributed task scheduling function, which can assign tasks to different executors for execution to improve task execution efficiency; XXL-Job also provides task executors that can be deployed on different servers to implement distributed task execution; XXL-Job also provides a task tracking function, through which the execution status and results of tasks can be viewed in real time, making it convenient for users to monitor and manage tasks; and XXL-Job also provides a task scheduling center for managing and scheduling tasks, allowing users to add, delete, modify tasks, and view task execution status through the task scheduling center.

[0176] Step 310: Send instructions.

[0177] Exemplarily, after determining the dependency graph, XXL-Job may send an instruction to the industry calculator 305 for triggering the industry calculator 305 to start calculation.

[0178] Step 311, calculate the index.

[0179] Exemplarily, at least one target indicator data may be calculated using the method provided in the aforementioned embodiment.

[0180] Step 312: Send the indicator.

[0181] Exemplarily, the industry calculator may send at least one target indicator data to Kafka 302 .

[0182] Step 313: Send the target identifier.

[0183] Exemplarily, Kafka 302 may send a target identifier of at least one target indicator data to the real-time monitoring module.

[0184] Step 314: reschedule the task.

[0185] Exemplarily, at this time, the real-time monitoring module can trigger XXL-Job to schedule the warning task so that XXL-Job can generate model update warning information.

[0186] Step 315: Send warning information.

[0187] For example, XXL-Job can generate model update warning information and send the information to the warning module, thereby prompting the researcher to confirm whether to update the profit split model.

[0188] It should be noted that Kafka and XXL-Job can also be replaced by other message middleware and task scheduling platforms.

[0189] Through the above process, real-time monitoring of basic indicator data in the financial field is achieved, and real-time calculation of indicator data associated with industry calculators can be triggered. In addition, early warning information can be automatically generated, thereby improving the automatic early warning of the update status of the profit split model.

[0190] As can be seen from the above, in the updating method of the investment model provided by the embodiment of the present application, if at least one target indicator data includes indicator data of the target type, and the fluctuation degree of the target indicator data is greater than or equal to the degree threshold, then the model update warning information is generated and output to indicate that the investment model is updated at least based on the target association data and / or the target indicator data, and the model update condition includes at least one target indicator data including indicator data of the target type, and the fluctuation degree of the target indicator data is greater than or equal to the preset threshold. In this way, through the above operation, the automatic warning of the investment model is realized, and by adjusting the target type and the degree threshold, the automatic warning processing of the investment model can be realized more flexibly, thereby realizing the diversified warning processing of the investment model.

[0191] Figure 4 A schematic diagram of a process of adjusting the profit splitting model of individual stocks according to an embodiment of the present application is shown in FIG. Figure 4 As shown, the process may include the following steps:

[0192] Step 401, start.

[0193] Step 402: Detect industry indicators.

[0194] Exemplarily, the industry indicator may be a basic financial indicator of the financial industry; exemplary, the change state of the basic financial indicator may be detected by the method provided in the aforementioned embodiment.

[0195] Step 403: trigger the industry calculator to calculate.

[0196] Exemplarily, when it is detected that a basic financial indicator is updated, the industry calculator may be triggered to perform calculations, thereby obtaining at least one target financial indicator.

[0197] Step 404: Determine whether the individual stock profit split model warning is triggered.

[0198] Exemplarily, if the value of at least one target financial indicator is greater than or equal to a preset threshold, an individual stock profit split model warning may be triggered; if the value of at least one target financial indicator is less than the preset threshold, an individual stock profit split model warning may not be triggered.

[0199] Exemplarily, if it is determined that the individual stock profit split model warning is triggered, model update warning information may be generated.

[0200] Step 405: Send a model adjustment alert to the researcher.

[0201] Exemplarily, the model alarm may be the model update warning information in the aforementioned embodiment.

[0202] For example, researchers may be notified by email or phone call to remind them to adjust the individual stock profit split model, thereby achieving real-time early warning of updates to the individual stock profit investment model.

[0203] In actual applications, since the researcher's prediction of the data on which the individual stock profit split model is based is based on the change pattern of current industry data over time, indicators related to designated industries such as the financial industry will be continuously obtained. Researchers need to make real-time adjustments to the predicted data of the individual stock profit split model based on the updated indicators.

[0204] The embodiment of the present application provides a real-time warning mechanism required by researchers when faced with the update of individual stock profit split model, that is, when certain pre-set target financial indicators are updated, if these target financial indicators meet the model update conditions, the researchers will be automatically reminded to update the individual stock profit split model.

[0205] Step 406: The researcher adjusts the individual stock profit split model.

[0206] Step 407, end.

[0207] Through the above process, the basic financial industry parameters corresponding to the adjustment of the individual stock profit split model are monitored, and the indicator data that triggers the individual stock profit split model is automatically calculated, thereby reducing the time and labor costs of updating the individual stock profit split model; and through the above process, the real-time monitoring ability of the researcher of the individual stock profit split model can also be improved, so that the researcher can correct the model in time to improve the accuracy of the model; in the above process, the industry calculator can be triggered to calculate the basic financial indicators to obtain complex derivative indicators, thereby providing data support for the update of the individual stock profit split model.

[0208] Based on the above embodiments, the present application also provides an investment model updating device. Figure 5 A schematic diagram of the structure of the updating device of the investment model provided in the embodiment of the present application, such as Figure 5 As shown, the updating device 5 of the investment model may include:

[0209] The acquisition module 501 is used to acquire target associated data in an updated state if at least one industry associated data update is detected; wherein the industry associated data is at least associated with a specified industry;

[0210] A determination module 502 is used to determine at least one target indicator data associated with the target associated data; wherein the target indicator data is associated with the revenue status of a specified industry in at least one time period;

[0211] The updating module 503 is used to update the investment model associated with the specified industry based on the industry-related data and / or the target indicator data if at least one target indicator data satisfies the model updating condition.

[0212] In some embodiments, the determination module 502 is used to determine a dependency graph between industry parameters; wherein the industry parameters are associated with a specified industry; the industry parameters include target association data;

[0213] The determination module 502 is further used to calculate the target associated data based on the dependency graph to obtain at least one target indicator data.

[0214] In some embodiments, the acquisition module 501 is used to acquire a set of calculation formulas for characterizing the calculation relationship between industry parameters;

[0215] The determination module 502 is used to integrate the association relationship between the industry parameters associated with the calculation formulas in the calculation formula set to obtain a dependency graph.

[0216] In some embodiments, the determination module 502 is used to determine the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph; based on the calculation order, at least the target-related data is calculated by the calculation formula in the calculation formula set to obtain at least one target indicator data.

[0217] In some embodiments, the determination module 502 is used to analyze the industry parameters in the dependency graph through a topological sorting algorithm to determine the dependencies between the industry parameters; based on the dependencies and the corresponding relationships, determine the calculation order; wherein the corresponding relationship includes the corresponding relationship between the industry parameters in the dependency graph and the calculation formulas in the calculation formula set.

[0218] In some embodiments, the determination module 502 is used to generate and output model update warning information if at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a degree threshold, to indicate that the investment model is updated based on at least the target-associated data and / or the target indicator data; wherein the model update condition includes that at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a preset threshold.

[0219] The embodiment of the present application also provides an electronic device, Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 6The electronic device 6 includes a processor 601 and a memory 602; the memory 602 stores a computer program; when the computer program is executed by the processor 601, the investment model updating method as described above can be implemented.

[0220] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored; when the computer program is executed by a processor of an electronic device, the investment model updating method as described in any of the above can be implemented.

[0221] An embodiment of the present application also provides a computer program product, which includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement the investment model updating method as described in any of the above.

[0222] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0223] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0224] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0225] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0226] It should be noted that the above-mentioned computer-readable storage medium can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM) and other memories; it can also be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0227] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0228] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0229] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus necessary general hardware nodes, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0230] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0231] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0232] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0233] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for updating an investment model, characterized in that: The method comprises: If at least one industry-related data update is detected, obtaining target-related data in an updated state; wherein the industry-related data is at least associated with a designated industry; Determine at least one target indicator data associated with the target-related data; wherein the target indicator data is associated with the revenue status of the specified industry in at least one time period; If the at least one target indicator data satisfies the model update condition, the investment model associated with the designated industry is updated based on the target association data and / or the target indicator data.

2. The method according to claim 1, characterized in that: The determining of at least one target indicator data associated with the target associated data includes: Determine a dependency graph between industry parameters; wherein the industry parameters are associated with the specified industry; and the industry parameters include the target association data; The target-related data is calculated based on the dependency graph to obtain the at least one target indicator data.

3. The method according to claim 2, characterized in that The step of determining the dependency graph between industry parameters includes: Obtaining a set of calculation formulas for characterizing the calculation relationship between the industry parameters; The association relationships between the industry parameters associated with the calculation formulas in the calculation formula set are integrated to obtain the dependency graph.

4. The method according to claim 2, characterized in that: The calculating the target-related data based on the dependency graph to obtain the at least one target indicator data includes: Determining a calculation order of calculation formulas in a set of calculation formulas associated with the dependency graph; Based on the calculation order, at least the target-related data is calculated using a calculation formula in the calculation formula set to obtain the at least one target indicator data.

5. The method according to claim 4, characterized in that The determining of the calculation order of the calculation formulas in the calculation formula set associated with the dependency graph includes: Analyze the industry parameters in the dependency graph by a topological sorting algorithm to determine the dependency relationship between the industry parameters; Based on the dependency and the corresponding relationship, the calculation order is determined; wherein the corresponding relationship includes the corresponding relationship between the industry parameters in the dependency graph and the calculation formulas in the calculation formula set.

6. The method according to claim 1, characterized in that If the at least one target indicator data satisfies the model update condition, updating the investment model associated with the designated industry based on the target association data and / or the target indicator data includes: If the at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a degree threshold, generate and output model update warning information to indicate that the investment model is updated at least based on the target-associated data and / or the target indicator data; wherein the model update condition includes that the at least one target indicator data includes indicator data of a target type, and the degree of fluctuation of the target indicator data is greater than or equal to a preset threshold.

7. An investment model updating device, characterized in that: The updating device of the investment model comprises: An acquisition module, configured to acquire target associated data in an updated state if at least one industry associated data update is detected; wherein the industry associated data is at least associated with a designated industry; A determination module, configured to determine at least one target indicator data associated with the target associated data; wherein the target indicator data is associated with the revenue status of the specified industry in at least one time period; An updating module is used to update the investment model associated with the specified industry based on the target association data and / or the target indicator data if the at least one target indicator data satisfies the model updating condition.

8. An electronic device, characterized in that: The electronic device comprises a processor and a memory; a computer program is stored in the memory; when the computer program is executed by the processor, the method for updating the investment model as described in any one of claims 1 to 6 can be implemented.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program; when the computer program is executed by a processor of an electronic device, the method for updating the investment model as described in any one of claims 1 to 6 can be implemented.

10. A computer program product, characterized in that The program product includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement the investment model updating method as described in any one of claims 1 to 6.

Images