Activity decision generation method and device based on decision model, equipment and medium

Abstract

The application discloses an activity decision generation method and device based on a decision model, equipment and a medium. The method is applied to an intelligent decision model, and the method comprises the following steps: acquiring corresponding actual parameters and standard parameters from a preset data source according to business requirements; matching a target deviation algorithm corresponding to the actual parameters and the standard parameters according to the actual parameters and the standard parameters; calculating a deviation value between the actual parameters and the standard parameters according to the target deviation algorithm; matching a corresponding event value according to the deviation value, and determining a corresponding execution activity according to the event value. The method can solve the problem that the prior art cannot efficiently and automatically make a decision.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent decision-making, and in particular to a method, apparatus, device, and medium for generating activity decisions based on a decision-making model. Background Technology

[0002] Currently, most organizations' decision-making systems still revolve around human managers, relying on accumulated experience and structured analytical frameworks. They heavily depend on managers' subjective judgment, value orientations, and comprehensive assessment capabilities of complex environments. This system exhibits clear hierarchical division of labor and process-oriented characteristics, strictly adhering to pre-set rules and steps, requiring multi-departmental and multi-level collaboration. However, this traditional model relies on manual, step-by-step information transmission, leading to information distortion, inefficient processes, and delayed decision-making response. It struggles to adapt to the needs of organizational digital transformation and real-time online operations, and is ill-equipped to handle complex business scenarios, rendering existing technologies incapable of efficiently and automatically making decisions. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and medium for generating activity decisions based on a decision model, aiming to solve the problem that existing technologies cannot efficiently and automatically make decisions.

[0004] In a first aspect, embodiments of the present invention provide an activity decision generation method based on a decision model, applied to an intelligent decision model, comprising: obtaining corresponding actual parameters and standard parameters from a preset data source according to business requirements; matching the actual parameters and the standard parameters with a corresponding target deviation algorithm; calculating the deviation value between the actual parameters and the standard parameters according to the target deviation algorithm; matching the deviation value with a corresponding event value; and determining the corresponding execution activity according to the event value.

[0005] Secondly, embodiments of the present invention also provide an activity decision generation device based on a decision model. The device is applied to an intelligent decision model and includes: an acquisition unit, configured to acquire corresponding actual parameters and standard parameters from a preset data source according to business requirements; a matching unit, configured to match a corresponding target deviation algorithm according to the actual parameters and the standard parameters; a calculation unit, configured to calculate the deviation value between the actual parameters and the standard parameters according to the target deviation algorithm; and a determination unit, configured to match a corresponding event value according to the deviation value and determine a corresponding execution activity according to the event value.

[0006] Thirdly, embodiments of the present invention also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0007] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the above-described method.

[0008] This invention provides a method, apparatus, device, and medium for generating activity decisions based on a decision model, applied to an intelligent decision model. The method includes: obtaining corresponding actual parameters and standard parameters from a preset data source according to business requirements; matching the actual parameters and standard parameters with a corresponding target deviation algorithm; calculating the deviation value between the actual parameters and standard parameters according to the target deviation algorithm; matching the deviation value with a corresponding event value; and determining the corresponding execution activity based on the event value. This invention obtains corresponding actual parameters and standard parameters from a preset data source and automatically matches them with corresponding deviation algorithms to obtain highly compatible deviation algorithms, avoiding result distortion due to algorithm mismatch. Based on the calculated deviation value, the business activity to be executed is determined from a predefined activity library to achieve automated decision-making, improve decision-making efficiency and accuracy, and adapt to complex and ever-changing business scenarios. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0011] Figure 2 This is a schematic diagram of the first sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0012] Figure 3 This is a schematic diagram of the second sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0013] Figure 4 A schematic diagram of the third sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0014] Figure 5 A schematic diagram of the fourth sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0015] Figure 6A schematic diagram of the fifth sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0016] Figure 7 A schematic diagram of the sixth sub-process of the activity decision generation method based on a decision model provided in an embodiment of the present invention;

[0017] Figure 8 A schematic block diagram of an activity decision generation device based on a decision model provided in an embodiment of the present invention;

[0018] Figure 9 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0021] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0023] Please see Figure 1 , Figure 1This is a flowchart illustrating the activity decision generation method based on a decision model provided in this embodiment of the invention. The activity decision generation method based on a decision model in this embodiment can be applied to an intelligent decision model, which can be deployed in an intelligent decision system or a corresponding APP. The intelligent decision model includes a perception module, an identification module, and a response module. The perception module acquires corresponding parameters, and the identification module makes a decision judgment. The response module matches the corresponding activity based on the decision judgment result of the identification module. The application can subscribe to the intelligent decision model from a decision model marketplace to receive decision services. For example, a hospital can subscribe to a decision model and use it to provide corresponding diagnostic services based on the patient's examination data. By using an intelligent decision model with this method, automated decision-making can be achieved, improving decision efficiency and accuracy, while adapting to complex and ever-changing business scenarios.

[0024] Figure 1 This is a flowchart illustrating the activity decision generation method based on a decision model provided in an embodiment of the present invention. As shown in the figure, the method includes the following steps S110-S140.

[0025] S110. Obtain the corresponding actual parameters and standard parameters from the preset data source according to business requirements.

[0026] In this embodiment, the business requirement is determined by the application party (user). For example, in the field of medical diagnosis, the business requirement might be to determine whether a patient has hypertension based on their blood pressure data. The preset data source is a place capable of storing data. In this embodiment, the preset data source is a database such as a metadata database, knowledge database, information database, event knowledge database, and intelligence database provided by a data marketplace. The actual parameters are real data generated during business operation and can be obtained by subscribing to the preset data source. For example, in the field of medical diagnosis, the actual parameters might be a patient's systolic and diastolic blood pressure data, which can be measured by medical devices and uploaded to a database for decision-making models to subscribe to. The standard parameters are pre-set benchmark values ​​used to measure whether the actual parameters meet the requirements. These can also be obtained by subscribing to the preset data source. For example, in the field of medical diagnosis, the standard parameters might be diagnostic criteria for hypertension (such as systolic blood pressure greater than 140 mmHg or diastolic blood pressure greater than 90 mmHg). These standards can be formulated by medical experts and uploaded to a data marketplace. The perception module of the intelligent decision-making model obtains corresponding actual and standard parameters from a preset data source based on business requirements. Specifically, the model analyzes the business requirements to determine the necessary parameters and searches or subscribes to the preset data source to obtain the corresponding actual and standard parameters. By obtaining the corresponding actual and standard parameters according to business requirements, a data foundation is provided for subsequent activity generation.

[0027] In one embodiment, such as Figure 2 As shown, steps S1101-S1103 are included before step S110.

[0028] S1101. Generate corresponding training execution activities based on the actual training parameters and standard training parameters in the training dataset;

[0029] S1102. Compare the training execution activity with the training label activity in the training dataset to generate error information;

[0030] S1103. Adjust the corresponding model parameter values ​​according to the error information to determine the intelligent decision-making model.

[0031] In this embodiment, after the developer constructs a decision model instance, it needs to be trained before being put into use. Specifically, the developer configures the target value, actual value, bias algorithm, event (value), and execution activity. The target value, actual value, and event value are subscribed to from a preset data source, while the bias algorithm is subscribed to from an algorithm marketplace. Once each module has completed its subscription and configuration, the editing of a decision model instance is complete. During editing, basic information about the decision model needs to be filled in, such as its name, industry, functional description, and remarks. Then, training data is input into the edited decision model, which is trained based on the training data. Specifically, based on the actual training parameters and standard training parameters in the training dataset, corresponding training execution activities are generated. The decision model calculates the bias value based on the actual training parameters and standard training parameters, and matches the corresponding event value with the bias value to determine the corresponding training execution activity. The training execution activity is compared with the training label activity corresponding to the actual training parameters and standard training parameters in the training dataset to obtain its error information. The corresponding model parameter values ​​are adjusted based on the error information. Specifically, the model parameter values ​​can be adjusted and optimized based on the error information using loss functions, error functions, etc., to minimize the error information. For example, error information can be propagated from the output layer to the input layer through backpropagation, the gradient of each parameter can be calculated, and the parameter values ​​can be updated to obtain the best-performing model, which is then identified as the intelligent decision-making model. The model learns from the training data, gradually optimizing its parameters to improve the accuracy of model decisions. In this embodiment, after the intelligent decision-making model meets the training requirements, it enters the release state. Before release, it needs to check whether various configurations are legal, including the continuity of bias terms, whether the algorithm input parameters are configured completely, and generate a version number. After the legality check, it can be released to the decision model marketplace and made visible to the application layer. The application layer can view and subscribe to the intelligent decision-making model through the decision model marketplace. When the application calls the intelligent decision-making model through the application layer, the decision model software starts executing S110 and the subsequent steps according to the business requirements passed by the application layer.

[0032] In one embodiment, such as Figure 3 As shown, step S1103 further includes steps S11031-S11032.

[0033] S11031. Determine whether the accuracy of the training execution activities generated by the adjusted intelligent decision-making model has reached the preset accuracy.

[0034] S11032. If the target is not met, continue to adjust the model parameter values ​​based on the training dataset.

[0035] In this embodiment, accuracy is an important metric for measuring model performance, representing the proportion of correctly predicted samples on the training dataset out of the total number of samples. The preset accuracy can be set according to business needs or application requirements, and is not limited thereto. After each model parameter adjustment, the adjusted model is used to predict on the training dataset, generating training execution activities. These are compared with the training labeled activities to determine their correctness, thus calculating the accuracy of these training execution activities. The calculated accuracy is compared with the preset normality rate. If the calculated accuracy is lower than the preset normality rate, it indicates that the model's performance under the current parameters has not yet reached expectations. The model parameter values ​​are then adjusted further based on the training dataset. For example, the gradient of the parameters is calculated based on the loss function (such as mean squared error, cross-entropy, etc.), and the parameter values ​​are updated accordingly. After parameter adjustment, the model is used again to predict on the training dataset, and a new accuracy is calculated, until the model's accuracy reaches or exceeds the preset normality rate. By judging whether the accuracy of the training execution activities generated by the adjusted intelligent decision-making model reaches the preset normal rate, and deciding whether to continue adjusting the model parameter values ​​based on the comparison results, it can be ensured that the model is continuously optimized during the training process and eventually reaches a satisfactory performance standard.

[0036] S120. Target deviation algorithm corresponding to matching the actual parameters with the standard parameters.

[0037] In this embodiment, the target deviation algorithm is used to calculate the deviation between the actual parameter and the standard parameter. It is understood that different business scenarios and data types may require different deviation algorithms for calculation. For example, for numerical data, a simple subtraction algorithm may be used to calculate the deviation; while for more complex data types or business scenarios, advanced algorithms such as neural networks or large models may be needed for deviation calculation. Therefore, it is necessary to match the corresponding target deviation algorithm according to the actual parameter and the standard parameter. Specifically, the perception module can automatically select or match the most suitable deviation algorithm from the algorithm market based on the attribute information of the actual parameter and the standard parameter (such as data type, range, precision, etc.) and the label and input parameter requirements of the deviation algorithm. For example, if the actual parameter and the standard parameter are numerical values ​​corresponding to a patient's blood pressure, then since blood pressure data is numerical data and what needs to be compared is the magnitude relationship between the actual value and the standard value, a simple subtraction algorithm can be selected as the target deviation algorithm. By automatically matching the most suitable target deviation algorithm according to the characteristics of the actual parameter and the standard parameter, the accuracy and effectiveness of the deviation calculation are ensured.

[0038] In one embodiment, such as Figure 4 As shown, step S120 further includes steps S121-S122.

[0039] S121. Filter out an initial deviation algorithm set that is within a preset similarity range based on the attribute information of the actual parameters and the standard parameters;

[0040] S122. Based on the data types of the actual parameters and the standard parameters, the target deviation algorithm is selected from the initial deviation algorithm set.

[0041] In this embodiment, the perception module filters target deviation algorithms from the algorithm market. It's important to note that each deviation algorithm is labeled with associated attribute tags. These tags describe the applicable data types and business scenarios of the algorithm. Therefore, the algorithm market can be used to filter based on the attribute information of the actual parameters and the standard parameters. For example, the perception module analyzes the attribute information of actual blood pressure data and diagnostic criteria, such as the data being numerical and the business domain being medical diagnosis. The similarity between this attribute information and the tags of various deviation algorithms in the algorithm market is calculated. For example, algorithms related to medical diagnosis and numerical data processing algorithms will have high similarity. Algorithms with similarity within a preset range, such as subtraction algorithms, mean algorithms, and neural network algorithms, are selected to form an initial deviation algorithm set. The preset similarity range can be set according to specific application requirements and is not limited thereto. The target deviation algorithm is then selected from the initial deviation algorithm set based on the data type of the actual parameters and the standard parameters, where the data type refers to the specific form of the data, such as numerical, Boolean, or string types. The initial set of deviation algorithms is used to select the deviation algorithm that best matches the data type. For example, if the number is numerical, then the subtraction algorithm is selected as the target deviation algorithm. By efficiently selecting the most suitable target deviation algorithm based on the attribute information of the actual parameters and standard parameters, as well as the data type, a highly suitable deviation algorithm is obtained, avoiding result distortion due to algorithm mismatch.

[0042] S130. Calculate the deviation value between the actual parameter and the standard parameter according to the target deviation algorithm.

[0043] In this embodiment, the deviation value calculation involves inputting the actual parameters into the target deviation algorithm and comparing them with standard parameters to determine the difference between the two. Specifically, the identification module passes the actual and standard parameters as inputs to the target deviation algorithm. The target deviation algorithm processes the input data according to its internal logic (such as subtraction, mean calculation, neural network inference, etc.), calculates and outputs the deviation value. The output deviation value has corresponding positive and negative values. For example, if the input data is actual systolic blood pressure: 130 mmHg and standard systolic blood pressure: 140 mmHg, then the output deviation value is -10 mmHg. By calculating the deviation value between the actual and standard parameters, accurate reference data is provided for subsequent decision analysis.

[0044] S140. Match the corresponding event value according to the deviation value, and determine the corresponding execution activity according to the event value.

[0045] In this embodiment, the event value is a classification or labeling representation of an event, used to identify events corresponding to different business scenarios or states. Specifically, each event has an event value, and each event value is bound to a preset deviation range. The corresponding event value is matched based on the deviation value. Specifically, the identification module matches the deviation value with the corresponding event value. For example, if the deviation value of systolic blood pressure is between 0-15 mmHg and the deviation value of diastolic blood pressure is between 0-10 mmHg, then the event value determined based on the deviation range is 1, which is "mild hypertension". This is then fed back to the response module. The response module determines the corresponding execution activity based on the event value. The response module determines the specific execution activity based on the event value matched by the identification module. The execution activity is a specific operation or response measure defined according to the event value. For example, for the "mild hypertension" event value, the execution activity might be a suggestion to adjust lifestyle. It is important to note that developers pre-configure the mapping relationship between events (values) and execution activities in the decision model. After an event is triggered, the decision model ultimately returns the activity corresponding to the event, thus completing the decision on the business activity. By matching the event values, corresponding execution activities are matched to achieve automated decision-making, thereby improving decision-making efficiency and accuracy.

[0046] In one embodiment, such as Figure 5 As shown, step S140 includes steps S141-S142.

[0047] S141. Match the deviation value with a preset deviation range to obtain the target deviation range;

[0048] S142. Determine the corresponding event value based on the target deviation range.

[0049] In this embodiment, the preset deviation range is a numerical range predefined based on business needs and domain knowledge, used to classify deviation values. For example, in hypertension diagnosis, different blood pressure deviation ranges can be set, such as "normal range," "mild hypertension," "moderate hypertension," and "severe hypertension." The target deviation range is obtained by matching the deviation value with the preset deviation range. Specifically, the identification module compares the calculated deviation value with the preset deviation range to determine which range the deviation value falls into. The deviation range into which the value falls is the target deviation range, which identifies the category or severity of the current deviation value. The corresponding event value is determined based on the target deviation range. Specifically, the deviation range is pre-bound to events, and each event is not assigned an event value. Therefore, the corresponding event value can be determined based on the target deviation range. By matching the calculated deviation value with the preset deviation range to determine the target deviation range, and thus the corresponding event value, it is ensured that different situations can be dynamically classified and responded to based on the magnitude and range of the deviation value.

[0050] In one embodiment, such as Figure 6 As shown, step S141 further includes steps S1411-S1413.

[0051] S1411. Determine the type of the deviation value, wherein the deviation value includes positive deviation, zero deviation, and negative deviation;

[0052] S1412. Based on the deviation value and its type, filter among several preset primary intervals to determine the target primary interval;

[0053] S1413. Based on the deviation value, filter among several preset secondary labels in the target primary interval to determine the target deviation interval.

[0054] In this embodiment, the deviation algorithm outputs both positive and negative values ​​for the deviation value, thus directly determining the type of the deviation value. The deviation value includes positive deviation (indicating the actual parameter is higher than the standard parameter), zero deviation (indicating the actual parameter is equal to the standard parameter), and negative deviation (indicating the actual parameter is lower than the standard parameter). Based on the deviation value and its type, a target first-level interval is determined by filtering through several preset first-level intervals. Specifically, the first-level interval is a predefined interval based on the type and approximate range of the deviation value, used for preliminary classification of the deviation value. The identification module matches the deviation value with the preset first-level intervals according to its type to determine the target first-level interval. For example, if the deviation value is positive, it matches the "positive deviation interval". The first-level interval includes several preset second-level labels to refine the classification of the deviation value. These second-level labels are typically based on business needs and domain knowledge, used to identify different business scenarios or states. For example, within the "positive deviation interval", the following second-level labels can be set: mild positive deviation, moderate positive deviation, and severe positive deviation. Within the target first-level interval, the identification module matches the specific value of the deviation value with the preset second-level labels to determine the target deviation interval. Precise decision-making is achieved by determining the target deviation range based on the deviation value.

[0055] In one embodiment, such as Figure 7 As shown, step S142 includes steps S1421-S1422.

[0056] S1421. Perform logical operations based on the deviation value to obtain the operation result;

[0057] S1422. Determine the event value corresponding to the target deviation interval based on the calculation result.

[0058] In this embodiment, the logical operation involves combining and analyzing multiple deviation items. For example, logical operators (such as AND and OR) are used to construct complex conditional expressions. The deviation values ​​can include deviations from various data types; therefore, it is necessary to more accurately determine whether the combination of deviation items meets the conditions for triggering an event. Logical operations are performed on the deviation values ​​to obtain the results. Specifically, for example, the result is true only when all deviation values ​​correspond to the same event value. The specific logical operators used can be set according to the specific scenario and are not limited thereto. The event value corresponding to the target deviation interval is determined based on the operation result. The event value corresponding to the target deviation interval is triggered only when the operation result is true. For example, if deviation value A (blood pressure deviation > 10 mmHg) AND deviation value B (heart rate deviation > 5 beats / minute) both correspond to the same event value, then that event value is determined as the final event value corresponding to the target deviation interval. By performing logical operations on the deviation values ​​to determine the final event value, accurate decision-making can still be achieved even in complex scenarios.

[0059] To further understand the activity decision generation method based on the decision model of the present invention, the following describes the process flow of activity decision generation:

[0060] The intelligent decision-making model can be deployed in an intelligent decision-making system or a corresponding application. It comprises an application layer, a service layer, and a facility layer. The application layer is the user of the intelligent decision-making model, calling relevant decision-making services via HTTP. The service layer includes intelligent decision-making model management, scheduling and execution, and data and algorithm interfaces. The management component implements modules for creating, editing, training, testing, and publishing the intelligent decision-making model, as well as displaying detailed information about each node (data) within the model. The intelligent decision-making model scheduling and execution service reads the node configuration information (configured deviation ranges, events, etc.) of the intelligent decision-making model via HTTP, calculates the information of each node sequentially based on actual values, target values, deviation values, events, and activities, and reports the results (intelligent data) to the application layer. Simultaneously, it saves the data generated during the process to the corresponding database in the facility layer. This achieves automated decision-making, improves decision-making efficiency and accuracy, and adapts to complex and ever-changing business scenarios.

[0061] Figure 8 This is a schematic block diagram of an activity decision generation device 200 based on a decision model provided in an embodiment of the present invention. Figure 8As shown, corresponding to the above-described activity decision generation method based on a decision model, the present invention also provides an activity decision generation device based on a decision model. This device includes a unit for executing the above-described activity decision generation method based on a decision model, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal. Specifically, please refer to... Figure 8 The activity decision generation device based on the decision model includes an acquisition unit 210, a matching unit 220, a calculation unit 230, and a determination unit 240.

[0062] The acquisition unit 210 is used to acquire the corresponding actual parameters and standard parameters from the preset data source according to business requirements.

[0063] In one embodiment, the acquisition unit 210 includes a generation unit, a comparison unit, and an adjustment unit.

[0064] The generation unit is used to generate corresponding training execution activities based on the actual training parameters and standard training parameters in the training dataset.

[0065] The comparison unit is used to compare the training execution activity with the training label activity in the training dataset and generate error information;

[0066] An adjustment unit is used to adjust the corresponding model parameter values ​​according to the error information to determine the intelligent decision-making model.

[0067] In one embodiment, the acquisition unit 210 includes a judgment unit and an adjustment subunit.

[0068] The judgment unit is used to determine whether the accuracy of the training execution activities generated by the adjusted intelligent decision-making model has reached the preset accuracy.

[0069] Adjust the sub-unit to continue adjusting the model parameter values ​​based on the training dataset if the target is not met.

[0070] The matching unit 220 is used to match the target deviation algorithm corresponding to the actual parameters and the standard parameters.

[0071] In one embodiment, the matching unit 220 includes a first filtering unit and a second filtering unit.

[0072] The first filtering unit is used to filter out an initial deviation algorithm set that is within a preset similarity range based on the attribute information of the actual parameters and the standard parameters.

[0073] The second filtering unit is used to filter the target deviation algorithm from the initial deviation algorithm set according to the data types of the actual parameters and the standard parameters.

[0074] The calculation unit 230 is used to calculate the deviation value between the actual parameter and the standard parameter according to the target deviation algorithm.

[0075] The determining unit 240 is used to match the corresponding event value according to the deviation value, and determine the corresponding execution activity according to the event value.

[0076] In one embodiment, the determining unit 240 includes a matching unit and a first determining unit.

[0077] The matching unit is used to match the deviation value within a preset deviation range to obtain the target deviation range;

[0078] The first determining unit is used to determine the corresponding event value based on the target deviation interval.

[0079] In this embodiment, the determining unit 240 includes a type determining unit, a third filtering unit, and a fourth filtering unit.

[0080] A type determination unit is used to determine the type of the deviation value, wherein the deviation value includes positive deviation, zero deviation, and negative deviation;

[0081] The third filtering unit is used to filter within several preset primary intervals based on the deviation value and its type to determine the target primary interval;

[0082] The fourth filtering unit is used to filter the target deviation range from a number of preset secondary labels in the target primary range based on the deviation value.

[0083] In this embodiment, the determining unit 240 includes a calculation unit and an event determining unit.

[0084] The arithmetic unit is used to perform logical operations based on the deviation value and obtain the calculation result;

[0085] An event determination unit is used to determine the event value corresponding to the target deviation interval based on the calculation result.

[0086] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned activity decision generation device 200 based on the decision model and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0087] The aforementioned decision generation device based on a decision model can be implemented as a computer program, which can, for example... Figure 9 It runs on the computer device shown.

[0088] Please see Figure 9 , Figure 9 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0089] See Figure 9 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0090] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform an activity-based decision generation method based on a decision model.

[0091] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0092] The internal memory 504 provides an environment for the execution of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an activity decision generation method based on a decision model.

[0093] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0094] The processor 502 is used to run a computer program 5032 stored in a memory to implement the steps of the above method.

[0095] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0096] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0097] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the steps of the method described above.

[0098] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0099] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0100] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0101] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0103] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An activity decision generation device based on a decision model, characterized in that, The device, applied to intelligent decision-making models, includes: The acquisition unit is used to acquire corresponding actual parameters and standard parameters from a preset data source according to business needs. The actual parameters include systolic blood pressure and diastolic blood pressure, and the standard parameters include reference values ​​corresponding to the systolic blood pressure and diastolic blood pressure. The matching unit is used to filter out an initial deviation algorithm set that falls within a preset similarity range based on the attribute information of the actual parameters and the standard parameters; and to filter out a target deviation algorithm from the initial deviation algorithm set based on the data types of the actual parameters and the standard parameters. The calculation unit is used to calculate the deviation value between the actual parameter and the standard parameter according to the target deviation algorithm, wherein the deviation value includes the deviation value of systolic blood pressure and the deviation value of diastolic blood pressure; A determining unit is configured to match the deviation value with a preset deviation interval to obtain a target deviation interval; determine the corresponding event value based on the target deviation interval; and determine the corresponding execution activity based on the event value. The preset deviation interval includes different blood pressure deviation intervals, including normal range, mild hypertension, moderate hypertension, and severe hypertension. The event value is a classification or labeling representation of an event, used to identify events corresponding to different business scenarios or states. Each event is assigned an event value, and each event value is bound to a preset deviation interval. The execution activity includes recommended lifestyle adjustments corresponding to the mild hypertension event value. The step of matching the deviation value within a preset deviation range to obtain the target deviation range includes: determining the type of the deviation value, wherein the deviation value includes positive deviation, zero deviation, and negative deviation; filtering the deviation value and its type within several preset primary ranges to determine the target primary range; and filtering the deviation value within several preset secondary labels in the target primary range to determine the target deviation range.

2. The apparatus according to claim 1, characterized in that, The determining unit is further configured to: Perform logical operations based on the deviation value to obtain the calculation result; The event value corresponding to the target deviation interval is determined based on the calculation result.

3. The apparatus according to claim 1, characterized in that, The acquisition unit is further configured to: Based on the actual training parameters and standard training parameters in the training dataset, generate corresponding training execution activities; The training execution activity is compared with the training label activity in the training dataset to generate error information; Adjust the corresponding model parameter values ​​based on the error information to determine the intelligent decision-making model.

4. The apparatus according to claim 3, characterized in that, The acquisition unit is further configured to: Determine whether the accuracy of the training execution activities generated by the adjusted intelligent decision-making model reaches the preset accuracy rate; If the desired result is not achieved, continue adjusting the model parameter values ​​based on the training dataset.

5. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the unit of the device as described in any one of claims 1-4.

6. A storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, can implement the units of the apparatus as described in any one of claims 1-4.

Images