Object behavior data processing method and device, computer equipment and storage medium

Abstract

The invention relates to an object behavior data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring behavior data recorded for a target object and uploaded by an electronic terminal associated with the target object in a target organization; performing state prediction on the target object based on the behavior data through a pre-trained state prediction model to obtain prediction states of the target object in different organization levels in the target organization; based on the hierarchy weight corresponding to the organization hierarchy, performing weighted fusion on the prediction state corresponding to the organization hierarchy to obtain a fusion state of the target object; and generating at least one piece of state prompt information for the target object based on the fusion state, and issuing the state prompt information to the electronic terminal, the state prompt information being used for prompting the target object to perform behavior adjustment so as to provide personalized management strategies and suggestions for the target object in a targeted manner.

Description

Technical Field

[0001] The present application relates to the field of intelligent campus management technology, and in particular to an object behavior data processing method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] In organizational management, organizational identification cards (such as student ID cards in schools and work badges in enterprises) mainly play the role of identity verification and are usually used to confirm the identities of employees and students and perform simple access control. These traditional organizational identification cards have relatively simple functions and cannot meet the growing needs of intelligent and personalized management.

[0003] In recent years, with the rapid development of the Internet of Things, big data analysis and artificial intelligence technology, the field of education, for example, is undergoing profound changes. In this context, the functions of electronic student cards, as key devices connecting students, teachers and campus management systems, are also constantly expanding and optimizing. The current electronic student cards can already integrate advanced functions such as real-time positioning and health monitoring, providing effective support for student safety and health management.

[0004] However, although these functions have improved the efficiency of campus management to a certain extent, there are still significant deficiencies in learning behavior analysis and personalized learning support. It is impossible to provide targeted status prompt information based on students' behavior and performance. The efficiency and accuracy of campus safety management are poor, which is not conducive to the realization of personalized education. Summary of the invention

[0005] Based on this, it is necessary to provide an object behavior data processing method, apparatus, computer equipment, computer-readable storage medium and computer program product that can provide personalized suggestions for the behavior and performance of the target object in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for processing object behavior data, comprising:

[0007] Obtaining behavioral data recorded for the target object uploaded by an electronic terminal associated with the target object in the target organization;

[0008] Performing state prediction for the target object based on the behavior data through a pre-trained state prediction model to obtain predicted states of the target object at different organizational levels in the target organization;

[0009] Based on the level weights corresponding to the organizational levels, weighted fusion is performed on the predicted states corresponding to the organizational levels to obtain a fusion state of the target object;

[0010] At least one status prompt information for the target object is generated based on the fusion state, and the status prompt information is sent to the electronic terminal, where the status prompt information is used to prompt the target object to adjust its behavior.

[0011] In one of the embodiments, the state prediction model includes state prediction sub-models corresponding to different organizational levels in the target organization;

[0012] The state prediction sub-model is trained in the following way:

[0013] Obtaining behavior sample data for a target object and the organizational level corresponding to the behavior sample data, and constructing a plurality of sample data sets based on the organizational level;

[0014] Inputting each of the sample data sets into the state prediction sub-model corresponding to the respective organizational level to perform feature extraction, and obtaining the hierarchical features corresponding to the organizational level of the behavior sample data;

[0015] Performing state prediction on the target object based on the hierarchical features through each of the state prediction sub-models to obtain a state prediction result of the target object in each of the organizational hierarchies;

[0016] Based on the hierarchical weights of the organizational levels corresponding to the state prediction sub-models, weighted fusion is performed on the state prediction results to obtain a fusion prediction result;

[0017] Based on the difference between the fusion prediction result and the actual result, each state prediction sub-model is trained until the end condition is reached, thereby obtaining each trained state prediction sub-model.

[0018] In one embodiment, sending the status prompt information to the electronic terminal includes:

[0019] Each of the status prompt information is split according to a preset rule to obtain a plurality of prompt sub-information corresponding to each status prompt information; the prompt sub-information has a corresponding information tag;

[0020] sorting the prompt sub-information according to the information tags;

[0021] According to the trigger instruction acting on the electronic terminal, the prompt sub-information is gradually or completely sent to the electronic terminal according to the information tag.

[0022] In one embodiment, the step of sending the prompt sub-information to the electronic terminal gradually or completely according to the information tag according to the trigger instruction acting on the electronic terminal includes:

[0023] Acquire a trigger instruction acting on the electronic terminal, and determine the type of the trigger instruction;

[0024] When the type of the trigger instruction is the first type, all the prompt sub-information is sent to the electronic terminal;

[0025] When the type of the trigger instruction is the second type, the value of a preset sending flag is accumulated by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction is returned until all the prompt sub-information is sent to the electronic terminal;

[0026] When the type of the trigger instruction is the third type, the value of the sending flag is decremented by one, and the prompt sub-information corresponding to the information tag that matches the value of the sending flag is sent to the electronic terminal, and the process returns to the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction until all the prompt sub-information is sent to the electronic terminal.

[0027] In one embodiment, the method further comprises:

[0028] Obtaining the real-time location of the electronic terminal;

[0029] When the real-time location is outside the preset area, a data storage instruction is sent to the electronic terminal; the data storage instruction is used to instruct the electronic terminal to save the collected behavior data locally;

[0030] When the real-time location is within a preset area, a data upload instruction is sent to the electronic terminal; the data upload instruction is used to instruct the electronic terminal to upload the behavior data collected in real time or stored locally.

[0031] In one embodiment, the method further comprises:

[0032] Obtaining real-time upload progress of the behavior data by the electronic terminal;

[0033] When the real-time uploading progress is completed, a data deletion instruction is sent to the electronic terminal; the data deletion instruction is used to instruct the electronic terminal to delete the uploaded behavior data.

[0034] In one embodiment, the method further comprises:

[0035] Encrypting the behavior data collected by the electronic terminal to obtain encrypted behavior data;

[0036] Obtaining encrypted data of the behavior;

[0037] The step of performing state prediction on the target object based on the behavior data through a pre-trained state prediction model to obtain the predicted state of the target object at different organizational levels in the target organization includes:

[0038] Decrypting the behavior encrypted data to obtain behavior decrypted data;

[0039] Based on the behavior decryption data, a state prediction is performed on the target object through a pre-trained state prediction model to obtain the predicted state of the target object in different organizational levels in the target organization.

[0040] In a second aspect, the present application further provides an object behavior data processing device, comprising:

[0041] A data acquisition module, used to acquire behavioral data recorded for a target object in a target organization uploaded by an electronic terminal associated with the target object;

[0042] A state prediction module, configured to perform state prediction for the target object based on the behavior data through a pre-trained state prediction model, and obtain predicted states of the target object at different organizational levels in the target organization;

[0043] A state fusion module, configured to perform weighted fusion on the predicted states corresponding to the organizational levels based on the level weights corresponding to the organizational levels, to obtain a fused state of the target object;

[0044] An information generation module is used to generate at least one status prompt information for the target object based on the fusion state, and send the status prompt information to the electronic terminal, wherein the status prompt information is used to prompt the target object to adjust its behavior.

[0045] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0046] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0047] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the method described above when executed by a processor.

[0048] The object behavior data processing method, device, computer equipment, computer-readable storage medium and computer program product can achieve accurate prediction of the behavior of the target object in different organizational levels by acquiring the behavior data recorded for the target object uploaded by the electronic terminal associated with the target object in the target organization, and predicting the state of the target object based on the behavior data through a pre-trained state prediction model, thereby obtaining the predicted state of the target object in different organizational levels in the target organization, which is beneficial to improving the accuracy of the state prediction result of the target object; at the same time, based on the level weight corresponding to the organizational level, the predicted state corresponding to the organizational level is weighted and fused to obtain the fused state of the target object, and at least one state prompt information for the target object is generated based on the fused state, and finally the state prompt information is sent to the electronic terminal, and the state prompt information is used to prompt the target object to adjust its behavior. Since the fused state integrates the correlation and importance differences between different organizational levels, when generating the state prompt information, not only the behavior data of the target object at the personal level can be considered, but also the behavior data of the higher organizational level can be integrated, thereby generating at least one state prompt information for the target object, so as to provide personalized management strategies and suggestions for the target object in a targeted manner, which is beneficial to the realization of personalized organizational management. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 An application environment diagram of an object behavior data processing method in one embodiment;

[0051] Figure 2 is a flow chart of a method for processing object behavior data in one embodiment;

[0052] Figure 3 A schematic diagram of a flow chart of a training process of a state prediction sub-model in one embodiment;

[0053] Figure 4 The following is a flow chart of a process of sending status prompt information in one embodiment;

[0054] Figure 5 is a structural block diagram of an object behavior data processing device in one embodiment;

[0055] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0057] The object behavior data processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the electronic terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0058] Among them, there are usually multiple electronic terminals 102, and the electronic terminals 102 are associated with different target objects to be managed. The electronic terminal 102 refers to a device that can access the server 104 and exchange data with the server 104, so as to record the behavior data of the corresponding target object. In specific implementation, the electronic terminal 102 can sense various types of behavior data acting on it or collected by it, and send the behavior data to the server 104, and is used to receive and display the status prompt information generated by the server after analyzing and processing the behavior data. For example, in the campus management scenario, the electronic terminal 102 mainly refers to the terminal configured on the student side or the teacher side and associated with the student or teacher, which can be expressed in the form of an electronic student ID / teacher ID; in the enterprise management scenario, the electronic terminal 102 can be a terminal configured on different employee sides and associated with employees, which can be expressed in the form of an electronic work badge. The electronic student ID / teacher ID / work badge is integrated with a variety of sensors and data acquisition devices, such as but not limited to one or more of a camera, a voice module, a positioning module, a data transmission module, and a communication module, so as to collect the behavior data of the target object in the target organization and upload it to the server 104, and receive the status prompt information generated by the server 104 for the behavior data of the management object.

[0059] In one implementation, an interactive module may also be integrated on the electronic terminal 102, such as including but not limited to one or more of a display screen, buttons, and a touch screen, so that the status prompt information sent by the server 104 can be displayed through the interactive module and the target object can interact with the server 104 through the interactive module.

[0060] It is understandable that in some other embodiments, depending on the specific application scenario, the electronic terminal 102 is not limited to the above-mentioned student ID, teacher ID, work badge and the like, but can also be a personal computer, laptop computer, tablet computer, smart phone, PDA (Personal Digital Assistant), Internet of Things device and portable wearable device and other devices that can collect behavioral data and receive status prompt information.

[0061] The server 104 is connected to multiple electronic terminals 102 as a central node for management, and is used to process and analyze the behavior data uploaded by the electronic terminals 102. In specific implementation, the server can be a backend management system set up in the target organization to collect, analyze, and process the behavior data, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0062] In an exemplary embodiment, Figure 2 As shown, a method for processing object behavior data is provided, and the method is applied to Figure 1 The server 104 in FIG. 1 is used as an example to illustrate. It is understandable that the method can also be applied to Figure 1 The terminal 102 in the embodiment may also be applied to a system including the terminal 102 and the server 104, and implemented through interaction between the terminal 102 and the server 104. The method of this embodiment includes:

[0063] Step 201: Obtaining behavior data recorded for a target object uploaded by an electronic terminal associated with the target object in a target organization.

[0064] Among them, the target organization refers to the scope of the target object that needs to be processed. In the field of organizational management, the target organization can be a school, enterprise, association or a specific cluster (such as a membership organization), or it can be a college or grade in a school, or a department in an enterprise.

[0065] The target object refers to the individual or group that needs to be managed within the target organization, such as students and teachers in schools, employees in enterprises, members of associations and specific clusters, etc. The electronic terminal associated with the target object means that there is an electronic terminal configured for each target object that needs to be managed. Usually, the data recorded on the electronic terminal is the behavior data of the target object.

[0066] Among them, behavioral data refers to information about the behavior of the target object collected or perceived through electronic terminals; in campus management, behavioral data can reflect students' learning and health conditions, etc., while in enterprise management, behavioral data can reflect employees' work conditions, etc. Taking campus management as an example, behavioral data can include but are not limited to learning data, status data, etc.; learning data can be the target object's learning ranking, academic performance, learning conditions (such as attendance, homework completion), etc., or data on problems related to learning and schoolwork, etc.; status data can be data on problems related to physical and psychological aspects of the target object, etc.

[0067] Exemplarily, the electronic terminal perceives the behavior data of the target object in the target organization through various modules, sensors or acquisition devices set thereon, or the target object in the target organization records the behavior data on the electronic terminal in an input manner through an interactive module, and the server obtains the behavior data recorded for the target object uploaded by the electronic terminal associated with the target object in the target organization.

[0068] Step 202 , using a pre-trained state prediction model to perform state prediction on a target object based on behavior data, and obtain predicted states of the target object at different organizational levels in the target organization.

[0069] Among them, the pre-trained state prediction model refers to a model built and trained using machine learning or deep learning algorithms. The state prediction model can predict the state of the target object within a period of time based on the input behavior data. The period of time can be in the near future or in the future. In specific implementation, the state prediction model can be implemented using an AI model (Artificial Intelligence, i.e., a large artificial intelligence model), a large language model, etc., to extract and analyze keywords in the behavior data to identify the current state of the target object or the current questions, so that the state prompt information can be generated in a targeted manner to provide status prompts for the target object.

[0070] The predicted state refers to the prediction result obtained by predicting the state of the target object through the pre-trained state prediction model.

[0071] The organizational level refers to the level at which the target objects in the target organization are divided according to a certain range, which is used to predict the state of the target object from different levels, so that the predicted behavior contains the characteristics of different organizational levels to improve the accuracy of the target object state prediction.

[0072] For example, in a school, the organizational level can be divided into school level, grade level, class level and individual level according to the school from large to small; among them, the school level refers to the prediction of the state of the target object based on the school level, which is used to reflect the behavior state of the target object in the whole school; the grade level refers to the prediction of the state of the target object based on the grade level, which is used to reflect the behavior state of the target object in the whole grade; the class level refers to the prediction of the state of the target object based on the class level, which is used to reflect the behavior state of the target object in the whole class; the individual level refers to the prediction of the state of the target object based on the individual level, which is used to reflect the behavior state of the target object itself. In some other embodiments, when dividing the levels, the levels can also be divided according to the subject dimension, such as the Chinese level, the mathematics level, the English level, etc., to reflect the learning status of the target object in the corresponding subject, and the levels can also be divided according to the time dimension, such as year, month, day or semester, etc., to reflect the continuous behavior state of the target object over time.

[0073] For example, in an enterprise, the organizational level can be divided into national level, district level, regional level, etc. according to the region, or divided into enterprise level, business unit level, branch level, etc. according to the business structure.

[0074] Exemplarily, after acquiring the behavior data of the target object, the server inputs the behavior data into a pre-trained state prediction model, processes the behavior data through the state prediction model to make a state prediction for the target object, and obtains the predicted state of the target object in different organizational levels in the target organization to reflect the corresponding behavior state of the target object in different organizational levels.

[0075] Step 203 , based on the level weights corresponding to the organizational levels, weighted fusion is performed on the predicted states corresponding to the organizational levels to obtain the fused state of the target object.

[0076] Among them, the hierarchical weight corresponding to the organizational level refers to the weight value determined according to the organizational level of the predicted state of the target object. The hierarchical weight is used to reflect the relative importance of different predicted states in the fusion state. If the hierarchical weight of the predicted state of a certain organizational level is larger, it means that the predicted state is more important in the fusion process and can better reflect the behavioral state of the target object, so more consideration needs to be given when performing fusion.

[0077] Among them, weighted fusion refers to the process of fusing the prediction states of multiple organizational levels according to the level weights. During the fusion process, weighted calculation is performed according to the level weights of the prediction states of each organizational level, and then the weighted prediction state values ​​are summarized. The summarization methods include but are not limited to screening, splicing, merging, etc., so as to obtain the final fusion state, so as to fully integrate the prediction results of each organizational level and improve the accuracy of the target object state prediction.

[0078] The fusion state refers to the state obtained by weighted fusion of different prediction states according to the hierarchical weights, which is used to comprehensively reflect the behavior of the target object.

[0079] Exemplarily, the server obtains the level weights corresponding to each organizational level, and based on the level weights corresponding to the organizational level, performs weighted fusion on the prediction states corresponding to each organizational level to obtain the fusion state of the target object.

[0080] Step 204: Generate at least one status prompt information for the target object based on the fusion status, and send the status prompt information to the electronic terminal.

[0081] Among them, the status prompt information refers to the information generated based on the fusion state of the target object, and the status prompt information is used to prompt the target object to adjust its behavior; in specific implementation, the status prompt information may include summary information of the state corresponding to the current behavior of the target object, and suggestion information for adjusting the current behavior. The suggestion information may include conclusions and specific response measures, strategies, etc.

[0082] For example, in a school, the status prompt information may be to make learning suggestions, teaching suggestions, correction suggestions, maintenance suggestions, or to answer questions raised by the target object; for another example, in an enterprise, the status prompt information may be to make work suggestions, work processing strategies, or to generate employee assessment prompts, performance prompts, etc.

[0083] The above-mentioned object behavior data processing method obtains the behavior data recorded for the target object uploaded by the electronic terminal associated with the target object in the target organization, and predicts the state of the target object based on the behavior data through a pre-trained state prediction model, so as to obtain the predicted state of the target object in different organizational levels in the target organization, which can realize the accurate prediction of the behavior of the target object in different organizational levels, and is conducive to improving the accuracy of the state prediction result of the target object; at the same time, based on the level weight corresponding to the organizational level, the predicted state corresponding to the organizational level is weighted and fused to obtain the fused state of the target object, and at least one state prompt information for the target object is generated based on the fused state, and finally the state prompt information is sent to the electronic terminal, and the state prompt information is used to prompt the target object to adjust its behavior. Since the fused state integrates the correlation and importance differences between different organizational levels, when generating the state prompt information, not only the behavior data of the target object at the personal level can be considered, but also the behavior data of the higher organizational level can be integrated, so as to generate at least one state prompt information for the target object, so as to provide personalized management strategies and suggestions for the target object in a targeted manner, which is conducive to the realization of personalized organizational management.

[0084] In one embodiment, the state prediction model includes state prediction sub-models corresponding to different organizational levels in the target organization.

[0085] Among them, the state prediction model of this embodiment is a composite model, which is composed of multiple state prediction sub-models corresponding to different organizational levels. The state prediction sub-model refers to a model that predicts the state of the target object from different organizational levels based on the behavioral data of the target object. Each state prediction sub-model can be implemented using the same or different algorithms.

[0086] Taking schools as an example, according to the hierarchical division of schools, we can construct status prediction sub-models corresponding to the school level, grade level, class level and individual level respectively.

[0087] like Figure 3 As shown in Figure 1, the state prediction sub-model is trained in the following way:

[0088] Step 301 : Obtain behavior sample data for a target object and the organizational level corresponding to the behavior sample data, and construct a plurality of sample data sets based on the organizational level.

[0089] The behavior sample data refers to the historical data obtained from the external server through electronic terminal records or servers for training the state prediction sub-model. For example, in school, the behavior sample data includes but is not limited to the behavior data of the target object in learning, campus life, etc. and its corresponding organizational level information, such as the basic information, learning records, attendance records and other data of the target object, and can also be the question data raised by the target object in response to certain questions.

[0090] The sample data set refers to a data set constructed according to the organizational level information of the behavior sample data. Each sample data set contains multiple behavior sample data belonging to the same organizational level, which are used to train the state prediction sub-model of the corresponding level. For example, the sample data set at the school level is composed of behavior sample data about the entire school, which is used to reflect the overall situation of all students; for another example, the sample data set at the grade level is composed of behavior sample data about the entire grade, which is used to reflect the overall situation of all students in a certain grade.

[0091] Exemplarily, the server obtains behavioral sample data for the target object and the organizational level corresponding to the behavioral sample data from an electronic terminal or external source, and divides each sample data into multiple data sets according to the organizational level to which each sample data belongs, so as to construct multiple sample data sets.

[0092] Step 302: Input each sample data set into the state prediction sub-model corresponding to the respective organizational level to extract features, and obtain the hierarchical features corresponding to the organizational level of the behavior sample data.

[0093] Among them, hierarchical features refer to features extracted from the sample data set by the state prediction sub-model and related to the behavioral state corresponding to the organizational level of the state prediction sub-model; they are used to describe the state performance of the target object in the organizational level. For example, hierarchical features at the school level can be the average grades, attendance rates, homework completion rates, etc. of all students in the entire school; for another example, hierarchical features at the class level can be the average grades, attendance rates, homework completion rates, etc. of all students in the entire class.

[0094] Exemplarily, the server inputs each sample data set into the state prediction sub-model corresponding to the respective organizational level to perform feature extraction, and obtains the hierarchical features corresponding to the organizational level of each behavior sample data.

[0095] Step 303: Perform state prediction on the target object based on the hierarchical features through each state prediction sub-model to obtain the state prediction results of the target object in each organizational level.

[0096] Among them, the state prediction result refers to the output obtained by the state prediction sub-model after predicting the state of the target object based on the hierarchical characteristics corresponding to each organizational level, which is used to represent the possible behaviors that the target object may take in each organizational level.

[0097] Exemplarily, the server calls the state prediction sub-model corresponding to each organizational level and takes the hierarchical features of each organizational level as input, performs state prediction on the target object through the state prediction sub-model, and obtains the state prediction results of the target object in each organizational level.

[0098] In some other embodiments, when performing state prediction, each state prediction sub-model may also first fuse the hierarchical features corresponding to each organizational level, and then input them into different state prediction sub-models for state prediction to obtain corresponding state prediction results. For example, for the state prediction sub-model at the school level, the hierarchical features corresponding to the school level, grade level, class level, and individual level may be assigned feature weights respectively, so that the hierarchical features of each level are weighted and fused according to the feature weights to obtain a fused hierarchical feature, so that the state prediction sub-model performs state prediction based on the fused hierarchical features to improve the prediction accuracy and generalization performance of the model.

[0099] Among them, the feature weight can be determined according to the correlation between the organizational level to which each level feature belongs and the organizational level of the state prediction sub-model. For example, for the state prediction sub-model at the school level, when the features are fused, the level features corresponding to the school level can be given a higher feature weight; for another example, for the state prediction sub-model at the individual level, when the features are fused, the level features corresponding to the individual level can be given a higher feature weight.

[0100] Step 304 , based on the hierarchical weights of the organizational levels corresponding to the state prediction sub-models, weighted fusion is performed on the state prediction results to obtain a fused prediction result.

[0101] Among them, weighted fusion of each state prediction result refers to multiplying the state prediction result of each state prediction sub-model by the corresponding hierarchical weight for weighting, and merging the weighted results to obtain a comprehensive fusion prediction result.

[0102] Among them, the fused prediction result refers to the output obtained by weighted fusion of the state prediction results of each state prediction sub-model. The fused prediction result integrates the behavioral hierarchical characteristics of different organizational levels and can more comprehensively reflect the possible behavioral performance of the target object.

[0103] Exemplarily, the server obtains the hierarchical weights of each organizational level, and based on the hierarchical weights corresponding to the organizational levels, performs weighted fusion on the prediction results of each state to obtain a fused prediction result.

[0104] Step 305: Train each state prediction sub-model based on the difference between the fusion prediction result and the actual result until the end condition is met, thereby obtaining each state prediction sub-model after training.

[0105] The actual result refers to the actual state of the target object. During the training process, the actual result is used to compare with the fusion prediction result to evaluate the accuracy of the state prediction model through the difference between the two, and the model is trained and optimized accordingly.

[0106] The end condition refers to the condition for ending model training during the model training process. When the end condition is met, the training process ends. The end condition may include but is not limited to reaching a preset accuracy rate, number of iterations, time limit, etc.

[0107] Among them, the trained state prediction sub-models refer to state prediction sub-models that can perform state prediction more accurately after training and optimization.

[0108] Exemplarily, the server determines the difference between the fused prediction result and the actual result, adjusts the model parameters of each state prediction sub-model according to the difference, and performs iterative training until the end condition is reached, thereby obtaining each state prediction sub-model after training.

[0109] In an exemplary embodiment, when performing model training, first, for the school-level status prediction sub-model, a random forest algorithm can be used to build an initial model, and the model is trained by inputting a sample data set corresponding to the school level into the school-level status prediction sub-model to obtain a trained school-level status prediction sub-model, and outputting the school-level status prediction result.

[0110] Next, based on the trained school-level state prediction sub-model, the model parameters of the school-level state prediction sub-model are used as the initial parameters of the grade-level state prediction sub-model by using the transfer learning method. The grade-level state prediction sub-model is trained using the sample data set corresponding to the grade level to obtain the trained grade-level state prediction sub-model, and the grade-level state prediction results are output.

[0111] Subsequently, based on the trained state prediction sub-model at the grade level, the model parameters of the state prediction sub-model at the grade level are used as the initial parameters of the state prediction sub-model at the class level by using the transfer learning method, and the state prediction sub-model at the class level is trained using the sample data set corresponding to the class level to obtain the trained state prediction sub-model at the class level, and the state prediction result at the class level is output. In this process, the model parameters can be further adjusted according to the difference between the state prediction results corresponding to the grade level and the class level.

[0112] Finally, based on the trained class-level state prediction sub-model, the deep learning algorithm is used to train the individual-level state prediction sub-model using the sample data set corresponding to the individual level to obtain the trained individual-level state prediction sub-model and output the individual-level state prediction result.

[0113] In this embodiment, by constructing sample data sets for different organizational levels, and performing feature extraction and state prediction respectively, the state prediction results are fused based on the hierarchical weights to obtain the fused state results, and finally the difference between the fused state results and the actual results is used for model training, which is beneficial to improving the training accuracy of the model, so that the trained model can more accurately and comprehensively capture the behavioral state of the target object, thereby improving the accuracy and reliability of the target object state prediction and the generalization ability of the model.

[0114] In one embodiment, Figure 4 As shown, the status prompt information is sent to the electronic terminal, including:

[0115] Step 401: split each status prompt information according to a preset rule to obtain a plurality of prompt sub-information corresponding to each status prompt information.

[0116] Among them, the preset rules refer to the standards or rules set in advance for splitting the status prompt information. In specific implementation, the preset rules can be determined based on the type and content of the status prompt information, or based on the attributes of the target object (such as identity, role, etc.), the functions of the electronic terminal, etc. For example, if the status prompt information is the answer information to the question asked to the target object, the preset rules can be the step sequence rules of the answer information, so as to split the answer information into multiple problem-solving steps according to the problem-solving steps; for another example, if the status prompt information is a learning suggestion provided to the target object, the preset rules can be the item rules of the learning suggestion, so as to split the learning suggestion into multiple different learning suggestions according to the items, etc.

[0117] Among them, the prompt sub-information refers to the more detailed information after the status prompt information is split according to the preset rules. Each status prompt information usually contains multiple prompt sub-information, and the prompt sub-information is executed or provided to the electronic terminal in a certain order to achieve the purpose of prompting. In this embodiment, the prompt sub-information has a corresponding information tag.

[0118] The information tag refers to an identifier used to identify and distinguish different prompt sub-information; the information tag may include but is not limited to the sequence number, name, function description and other information of each prompt sub-information.

[0119] Exemplarily, the server determines a preset rule for splitting the status prompt information, and splits each status prompt information based on the preset rule to obtain a plurality of prompt sub-information corresponding to each status prompt information.

[0120] Step 402, sorting the prompt sub-information according to the information tags.

[0121] Sorting refers to the process of arranging the prompt sub-information according to the information tags. In specific implementation, the sorting can be performed based on factors such as the logical relationship, execution order, and priority between the prompt sub-information.

[0122] Exemplarily, the server sorts each prompt sub-information according to the information tag of each prompt sub-information.

[0123] Step 403: according to the trigger instruction acting on the electronic terminal, the prompt sub-information is gradually or completely sent to the electronic terminal according to the information tags.

[0124] The trigger instruction of the electronic terminal refers to an instruction acting on the electronic terminal for requesting status prompt information or prompt sub-information. The trigger instruction can be triggered by the operation of the target object on the electronic terminal, or it can be automatically triggered by the electronic terminal according to preset conditions. In this embodiment, the trigger instruction can include but is not limited to click, touch and other operations made on the interactive module of the electronic terminal.

[0125] Among them, gradual distribution refers to the process of sending the prompt sub-information to the electronic terminal one by one or in batches according to the order or logic of the information tags, so that the electronic terminal can gradually display the status prompt information to ensure that each prompt sub-information is correctly understood and executed.

[0126] Among them, sending all refers to the process of sending all prompt sub-information of the status prompt information to the electronic terminal at one time, so as to quickly send the status prompt information.

[0127] Exemplarily, the server obtains a trigger instruction acting on the electronic terminal, and sends the prompt sub-information to the electronic terminal step by step or in its entirety according to the information tag based on the trigger instruction.

[0128] In this embodiment, the status prompt information is split according to preset rules, and corresponding information tags are assigned to the split prompt sub-information. The prompt sub-information is sorted according to the information tags to ensure the logic and orderliness between the prompt sub-information. Subsequently, the prompt sub-information is gradually or completely sent to the electronic terminal according to the trigger instruction, which is conducive to improving the flexibility and response speed of information processing.

[0129] In one embodiment, according to the trigger instruction acting on the electronic terminal, the prompt sub-information is gradually or completely sent to the electronic terminal according to the information tag, including:

[0130] Obtain a trigger instruction acting on the electronic terminal and determine the type of the trigger instruction.

[0131] When the trigger instruction is of the first type, all prompt sub-information is sent to the electronic terminal.

[0132] When the trigger instruction is of the second type, the value of a preset sending flag is added by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the process returns to the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction until all the prompt sub-information is sent to the electronic terminal.

[0133] When the trigger instruction is of the third type, the sending flag is decremented by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the process returns to the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction until all the prompt sub-information is sent to the electronic terminal.

[0134] The type of trigger instruction refers to that the trigger instruction can be divided into different categories according to its characteristics or functions, which is used to distinguish different operations and instructions used on the electronic terminal. In this embodiment, the types of trigger instructions include the first type, the second type and the third type. Different types determine different ways of sending prompt sub-information. Taking the sending of answer information generated for the question raised by the target object as an example, the first type of trigger instruction is used to instruct the server to send all steps of the answer information to the electronic terminal at one time, the second type of trigger instruction is used to instruct the server to send the next problem-solving step to the electronic terminal, and the third type of trigger instruction is used to instruct the server to send the previous problem-solving step to the electronic terminal.

[0135] Among them, the sending flag refers to a variable or identifier used to track the current sending progress; the value of the sending flag will increase or decrease with the reception of the second type or third type trigger instruction, thereby indicating the next prompt sub-information that should be sent.

[0136] Among them, the information tag matching the value of the sending flag bit refers to the information tag that is the same as or associated with the value of the current sending flag bit, so that the server can determine which prompt sub-information should be sent under the current sending progress by comparing the value of the sending flag bit with the information tag.

[0137] Exemplarily, the server obtains a trigger instruction acting on the electronic terminal, and parses the trigger instruction to determine the type of the trigger instruction.

[0138] If the trigger instruction is a first type of trigger instruction, it means that the target object obtains the status prompt information at one time, and the server sends all the prompt sub-information to the electronic terminal.

[0139] If the trigger instruction is a trigger instruction of the second type, the value of a preset sending flag is added by one, and the value of the sending flag is matched with the information tag of each prompt sub-information, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is determined, and the prompt sub-information is sent to the electronic terminal; at this time, if the prompt sub-information has not been fully sent or the end instruction is not detected, return to step 401 to continue to obtain the trigger instruction acting on the electronic terminal until all the prompt sub-information is sent to the electronic terminal.

[0140] If the trigger instruction is a trigger instruction of the third type, the value of the sending flag is decremented by one, and the value of the sending flag is matched with the information tag of each prompt sub-information, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is determined, and the prompt sub-information is sent to the electronic terminal, and the process returns to step 401 to continue to obtain the trigger instruction acting on the electronic terminal until all the prompt sub-information is sent to the electronic terminal or the server detects the end instruction, and the sending of the status prompt information is completed.

[0141] In this embodiment, by identifying the type of trigger instruction and issuing the prompt sub-information according to the corresponding type of trigger instruction, the prompt sub-information can be issued all at once to meet the target object's need to quickly view the prompt sub-information, or the prompt sub-information can be issued gradually so that the target object can view it gradually as needed to improve the progressiveness of information processing and user experience. The target object can also be allowed to backtrack and view the prompt sub-information that has been issued, which is conducive to enhancing the flexibility and convenience of information acquisition, and thus adapting to different information viewing needs.

[0142] In one embodiment, the method further includes:

[0143] Obtain the real-time location of the electronic terminal; when the real-time location is outside the preset area, send a data storage instruction to the electronic terminal; when the real-time location is within the preset area, send a data upload instruction to the electronic terminal.

[0144] Among them, the real-time location refers to the current geographical location information of the electronic terminal, which is used to determine whether the electronic terminal is located in a preset area. In specific implementation, the real-time location can be realized through the positioning model built into the electronic terminal. The positioning module can realize the positioning of the electronic terminal based on technologies such as Beidou, GPS (Global Positioning System), Wi-Fi (mobile hotspot), and LBS (Location Based Services).

[0145] Among them, the preset area refers to a pre-defined geographical range, which is used to distinguish whether the electronic terminal needs to upload behavioral data; when the real-time location of the electronic terminal is outside the preset area, the data storage operation will be performed; and when the real-time location is within the preset area, the data upload operation will be performed. In specific implementation, the preset area can be an area defined by the geographical location of the target organization, or it can be an area where the target object may appear. In some other embodiments, the division of the preset area can also be used to determine whether the target object is in school, on duty, etc., so as to achieve management of the target object.

[0146] Among them, the data storage instruction refers to a control instruction used to instruct the electronic terminal to save the collected behavior data locally. When saving the behavior data, it can be achieved through devices such as memory sticks, hard disks, memory cards, etc. built into the electronic terminal.

[0147] Among them, the data upload instruction refers to a control instruction used to instruct the electronic terminal to upload behavioral data collected in real time or stored locally, which can not only avoid data redundancy on the electronic terminal, but also reduce the risk of privacy leakage of the target object caused by local data leakage.

[0148] Exemplarily, the server obtains the real-time location of the electronic terminal through a positioning module built into the electronic terminal to determine whether the electronic terminal is within a preset area; when the real-time location of the electronic terminal is outside the preset area, the server sends a data storage instruction to the electronic terminal to instruct the electronic terminal to save the behavior data of the target object sensed or collected outside the preset area to a local storage device; when the real-time location of the electronic terminal is within the preset area, the server sends a data upload instruction to the electronic terminal to instruct the electronic terminal to upload the behavior data of the target object sensed or collected in real time or the behavior data stored locally to the server.

[0149] In this embodiment, by monitoring the real-time location of the electronic terminal in real time and adjusting the storage or upload strategy of the behavior data recorded by the electronic terminal for the target object according to the real-time location, when the electronic terminal is outside the preset area, the behavior data is saved locally. Once the electronic terminal enters the preset area, the behavior data is immediately uploaded to the server to ensure that the behavior data will not be excessively accumulated locally in the electronic terminal. This is beneficial for saving storage space and greatly reducing the risk of privacy leakage caused by long-term retention of behavior data on the electronic terminal.

[0150] In one embodiment, the method further includes:

[0151] Obtain the real-time upload progress of the electronic terminal for the behavior data; when the real-time upload progress is complete, send a data deletion instruction to the electronic terminal.

[0152] The real-time upload progress refers to the progress information of the electronic terminal uploading the behavior data. The real-time upload progress information may include but is not limited to the uploaded data volume, upload speed, remaining upload time, etc., so that the server can determine the upload progress of the behavior data.

[0153] Among them, upload completion refers to a status mark that all behavior data collected or stored by the electronic terminal have been uploaded, indicating that the electronic terminal has completed uploading all behavior data.

[0154] The data deletion instruction refers to a control instruction used to instruct the electronic terminal to delete the uploaded behavior data. When the real-time upload progress of the electronic terminal is completed, the server will issue a data deletion instruction to ensure that the uploaded data will not be stored repeatedly on the electronic terminal, thereby saving storage space and protecting data security.

[0155] Deletion refers to the process of removing the uploaded behavior data from the storage device of the electronic terminal. By performing the deletion operation, it can be ensured that the uploaded behavior data is no longer retained on the electronic terminal, avoiding data redundancy and duplication.

[0156] Exemplarily, the server determines whether the behavior data on the electronic terminal is completely uploaded to the server by obtaining the real-time upload progress of the behavior data by the electronic terminal; when the real-time upload progress of the behavior data is complete, the server sends a data deletion instruction to the electronic terminal to instruct the electronic terminal to delete the uploaded behavior data from the local storage device.

[0157] In this embodiment, by monitoring the real-time upload progress of the electronic terminal for the behavior data, and issuing a data deletion instruction to the electronic terminal after the behavior data of the electronic terminal is uploaded, the electronic terminal is controlled to delete the uploaded behavior data from the local. On the one hand, it can avoid redundancy and duplication of behavior data on the electronic terminal, so as to free up more storage space for the electronic terminal to save behavior data outside the preset area. On the other hand, it can further reduce the risk of data leakage.

[0158] In one embodiment, the above method further includes: encrypting the behavior data collected by the electronic terminal to obtain encrypted behavior data; obtaining the encrypted behavior data.

[0159] Based on this, based on the behavioral data, a pre-trained state prediction model is used to predict the state of the target object, and the predicted state of the target object at different organizational levels in the target organization is obtained, including:

[0160] The behavior encrypted data is decrypted to obtain the behavior decrypted data; based on the behavior decrypted data, a state prediction is performed on the target object through a pre-trained state prediction model to obtain the predicted state of the target object in different organizational levels in the target organization.

[0161] Encryption refers to the process of encrypting the behavior data uploaded by the electronic terminal, which is used to convert the behavior data into encrypted behavior data. In specific implementation, the encryption process can be implemented by using encryption algorithms through encryption chips and security elements built into the electronic terminal to protect the confidentiality and security of the behavior data and prevent unauthorized access and leakage.

[0162] Among them, behavior encrypted data refers to data that is obtained after the behavior data is encrypted and cannot be directly interpreted. The behavior encrypted data can only be restored to the original behavior data through the corresponding decryption process.

[0163] Decryption refers to the reverse process of encryption, that is, the process of decrypting the behavior encrypted data, which is used to convert the encrypted behavior encrypted data back to the original data, that is, the behavior decrypted data. Corresponding to the encryption process, the decryption process can also be implemented by using a decryption algorithm through a decryption chip, security element and other devices built into the server to ensure accurate interpretation of the behavior encrypted data.

[0164] The behavior decrypted data refers to the data obtained after the behavior encrypted data is decrypted and can be directly interpreted, that is, restored to the original behavior data.

[0165] Exemplarily, the server sends an encryption instruction to the electronic terminal, instructing the electronic terminal to use an encryption algorithm to encrypt the collected behavior data to obtain encrypted behavior data. Subsequently, the server obtains the encrypted behavior data and uses a decryption algorithm that matches the encryption algorithm to decrypt the encrypted behavior data to obtain decrypted behavior data. The decrypted behavior data is then input into a pre-trained state prediction model, and the decrypted behavior data is processed by the state prediction model to perform state prediction for the target object, thereby obtaining the predicted state of the target object in different organizational levels in the target organization to reflect the corresponding behavior state of the target object at different organizational levels.

[0166] In this embodiment, encryption processing is performed on the behavior data collected by the electronic terminal, which is beneficial to enhancing the confidentiality and security of the behavior data during transmission and reducing the risk of leakage of sensitive information during transmission.

[0167] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0168] Based on the same inventive concept, the embodiment of the present application also provides an object behavior data processing device for implementing the object behavior data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more object behavior data processing device embodiments provided below can refer to the limitations of the object behavior data processing method above, and will not be repeated here.

[0169] In an exemplary embodiment, Figure 5 As shown, an object behavior data processing device is provided, comprising: a data acquisition module 501, a state prediction module 502, a state fusion module 503 and an information generation module 504, wherein:

[0170] The data acquisition module 501 is used to acquire the behavior data recorded for the target object uploaded by the electronic terminal associated with the target object in the target organization.

[0171] The state prediction module 502 is used to perform state prediction on the target object based on the behavior data through a pre-trained state prediction model to obtain the predicted state of the target object in different organizational levels in the target organization.

[0172] The state fusion module 503 is used to perform weighted fusion on the predicted states corresponding to the organizational levels based on the level weights corresponding to the organizational levels to obtain the fused state of the target object.

[0173] The information generation module 504 is used to generate at least one state prompt information for the target object based on the fusion state, and send the state prompt information to the electronic terminal, where the state prompt information is used to prompt the target object to adjust its behavior.

[0174] In an optional embodiment, the state prediction model includes state prediction sub-models corresponding to different organizational levels in the target organization. The above-mentioned device also includes:

[0175] The model training module is used to obtain the behavior sample data for the target object and the organizational level corresponding to the behavior sample data, and construct multiple sample data sets based on the organizational level; input each sample data set into the state prediction sub-model corresponding to the respective organizational level for feature extraction, and obtain the hierarchical features corresponding to the organizational level of the behavior sample data; predict the state of the target object based on the hierarchical features through each state prediction sub-model, and obtain the state prediction results of the target object in each organizational level; based on the hierarchical weight of the organizational level corresponding to each state prediction sub-model, weightedly fuse each state prediction result to obtain a fused prediction result; train each state prediction sub-model based on the difference between the fused prediction result and the actual result until the end condition is met, and obtain each state prediction sub-model after training.

[0176] In an optional embodiment, the information generation module 504 is also used to split each status prompt information according to preset rules to obtain multiple prompt sub-information corresponding to each status prompt information; the prompt sub-information has a corresponding information tag; the prompt sub-information is sorted according to the information tag; and the prompt sub-information is gradually or completely sent to the electronic terminal according to the information tag according to the trigger instruction acting on the electronic terminal.

[0177] In an optional embodiment, the information generation module 504 is also used to obtain a trigger instruction acting on the electronic terminal and determine the type of the trigger instruction; when the type of the trigger instruction is the first type, all prompt sub-information is sent to the electronic terminal; when the type of the trigger instruction is the second type, the value of a preset sending flag is accumulated by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction is returned until all prompt sub-information is sent to the electronic terminal; when the type of the trigger instruction is the third type, the value of the sending flag is accumulated by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction is returned until all prompt sub-information is sent to the electronic terminal.

[0178] In an optional embodiment, the above device further includes:

[0179] A data transmission control module is used to obtain the real-time location of the electronic terminal; when the real-time location is outside the preset area, a data storage instruction is sent to the electronic terminal; the data storage instruction is used to instruct the electronic terminal to save the collected behavior data locally; when the real-time location is within the preset area, a data upload instruction is sent to the electronic terminal; the data upload instruction is used to instruct the electronic terminal to upload the behavior data collected in real time or stored locally.

[0180] In an optional embodiment, the above device further includes:

[0181] The data deletion control module is used to obtain the real-time upload progress of the electronic terminal for the behavior data; when the real-time upload progress is completed, a data deletion instruction is sent to the electronic terminal; the data deletion instruction is used to instruct the electronic terminal to delete the uploaded behavior data.

[0182] In an optional embodiment, the above device further includes:

[0183] The data encryption module is used to encrypt the behavior data collected by the electronic terminal to obtain the behavior encrypted data; obtain the behavior encrypted data.

[0184] The state prediction module 502 is also used to decrypt the behavior encrypted data to obtain the behavior decrypted data; based on the behavior decrypted data, a pre-trained state prediction model is used to perform state prediction on the target object to obtain the predicted state of the target object in different organizational levels in the target organization.

[0185] Each module in the above-mentioned object behavior data processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0186] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the behavior data of the target object, various prediction models, hierarchical weights, status prompt information, information labels, behavior sample data, etc. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for processing object behavior data is implemented.

[0187] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0188] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the object behavior data processing method of the above embodiment is implemented.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the object behavior data processing method of the above embodiment is implemented.

[0190] In one embodiment, a computer program product is provided, including a computer program, which implements the object behavior data processing method of the above embodiment when executed by a processor.

[0191] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0192] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0193] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0194] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing object behavior data, characterized in that: The method comprises: Obtaining behavioral data recorded for the target object uploaded by an electronic terminal associated with the target object in the target organization; Performing state prediction for the target object based on the behavior data through a pre-trained state prediction model to obtain predicted states of the target object at different organizational levels in the target organization; Based on the level weights corresponding to the organizational levels, weighted fusion is performed on the predicted states corresponding to the organizational levels to obtain a fusion state of the target object; At least one status prompt information for the target object is generated based on the fusion state, and the status prompt information is sent to the electronic terminal, where the status prompt information is used to prompt the target object to adjust its behavior.

2. The method according to claim 1, characterized in that The state prediction model includes state prediction sub-models corresponding to different organizational levels in the target organization; The state prediction sub-model is trained in the following way: Obtaining behavior sample data for a target object and the organizational level corresponding to the behavior sample data, and constructing a plurality of sample data sets based on the organizational level; Inputting each of the sample data sets into the state prediction sub-model corresponding to the respective organizational level to perform feature extraction, and obtaining the hierarchical features corresponding to the organizational level of the behavior sample data; Performing state prediction on the target object based on the hierarchical features through each of the state prediction sub-models to obtain a state prediction result of the target object in each of the organizational hierarchies; Based on the hierarchical weights of the organizational levels corresponding to the state prediction sub-models, weighted fusion is performed on the state prediction results to obtain a fusion prediction result; Based on the difference between the fusion prediction result and the actual result, each state prediction sub-model is trained until the end condition is reached, thereby obtaining each trained state prediction sub-model.

3. The method according to claim 1, characterized in that The sending the status prompt information to the electronic terminal includes: Each of the status prompt information is split according to a preset rule to obtain a plurality of prompt sub-information corresponding to each status prompt information; the prompt sub-information has a corresponding information tag; sorting the prompt sub-information according to the information tags; According to the trigger instruction acting on the electronic terminal, the prompt sub-information is gradually or completely sent to the electronic terminal according to the information tag.

4. The method according to claim 3, characterized in that: The step of sending the prompt sub-information to the electronic terminal gradually or completely according to the information tag according to the trigger instruction acting on the electronic terminal includes: Acquire a trigger instruction acting on the electronic terminal, and determine the type of the trigger instruction; When the type of the trigger instruction is the first type, all the prompt sub-information is sent to the electronic terminal; When the type of the trigger instruction is the second type, the value of a preset sending flag is accumulated by one, and the prompt sub-information corresponding to the information tag matching the value of the sending flag is sent to the electronic terminal, and the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction is returned until all the prompt sub-information is sent to the electronic terminal; When the type of the trigger instruction is the third type, the value of the sending flag is decremented by one, and the prompt sub-information corresponding to the information tag that matches the value of the sending flag is sent to the electronic terminal, and the process returns to the step of obtaining the trigger instruction acting on the electronic terminal and determining the type of the trigger instruction until all the prompt sub-information is sent to the electronic terminal.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtaining the real-time location of the electronic terminal; When the real-time location is outside the preset area, a data storage instruction is sent to the electronic terminal; the data storage instruction is used to instruct the electronic terminal to save the collected behavior data locally; When the real-time location is within a preset area, a data upload instruction is sent to the electronic terminal; the data upload instruction is used to instruct the electronic terminal to upload the behavior data collected in real time or stored locally.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtaining real-time upload progress of the behavior data by the electronic terminal; When the real-time uploading progress is completed, a data deletion instruction is sent to the electronic terminal; the data deletion instruction is used to instruct the electronic terminal to delete the uploaded behavior data.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Encrypting the behavior data collected by the electronic terminal to obtain encrypted behavior data; Obtaining encrypted data of the behavior; The step of performing state prediction on the target object based on the behavior data through a pre-trained state prediction model to obtain the predicted state of the target object at different organizational levels in the target organization includes: Decrypting the behavior encrypted data to obtain behavior decrypted data; Based on the behavior decryption data, a state prediction is performed on the target object through a pre-trained state prediction model to obtain the predicted state of the target object in different organizational levels in the target organization.

8. An object behavior data processing device, characterized in that: The device comprises: A data acquisition module, used to acquire behavioral data recorded for a target object in a target organization and uploaded by an electronic terminal associated with the target object; A state prediction module, configured to perform state prediction for the target object based on the behavior data through a pre-trained state prediction model, and obtain predicted states of the target object at different organizational levels in the target organization; A state fusion module, configured to perform weighted fusion on the predicted states corresponding to the organizational levels based on the level weights corresponding to the organizational levels, to obtain a fused state of the target object; An information generation module is used to generate at least one status prompt information for the target object based on the fusion state, and send the status prompt information to the electronic terminal, wherein the status prompt information is used to prompt the target object to adjust its behavior.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images