Virtual article operation method and device based on emotion tag and electronic equipment

Abstract

The embodiment of the invention discloses a virtual article operation method and device based on an emotion tag and electronic equipment. A specific embodiment of the method comprises the following steps: carrying out data preprocessing on a real-time service data sequence; determining an observation window according to the preprocessed business data sequence; determining an emotion label according to the target business data sequence; in response to the fact that the emotion tag is determined to be a negative emotion tag, negative adjustment control strategy information for the virtual article is generated according to current control strategy information corresponding to the virtual article and the emotion tag; in response to the fact that the emotion tag is determined to be a forward emotion tag, forward adjustment control strategy information for the virtual article is generated according to the current control strategy information and the emotion tag; and performing virtual article regulation and control on the virtual article according to the current control strategy information or the updated control strategy information. According to the implementation, the abnormal operation is effectively prevented and protected, the possible data risk is avoided, and the equipment safety is ensured.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and more particularly, to a method, an apparatus, and an electronic device for operating virtual items based on emotion tags. Background Art

[0002] For operations on virtual items (such as obtaining, updating, etc.), frequent operations are often required, that is, there are a large number of related operations per unit time. For frequent virtual item operations, it is difficult to comprehensively and effectively detect abnormal virtual item operations by manual means, and thus it is impossible to accurately and effectively control virtual items. Especially when there are abnormal virtual item operations, it is impossible to effectively prevent and protect against abnormal operations, which may result in data risks and device security risks.

[0003] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art. Summary of the Invention

[0004] This summary of the disclosure is intended to introduce concepts in a brief form, which will be described in detail in the following detailed implementation section. This summary of the disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] Some embodiments of the present disclosure propose a method, an apparatus, and an electronic device for operating virtual items based on emotion tags to solve one or more of the technical problems mentioned in the above background art section.

[0006] In a first aspect, some embodiments of the present disclosure provide a method for operating virtual items based on emotion tags, the method comprising: collecting a real-time service data sequence for a virtual item; performing data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; determining an observation window according to the preprocessed service data sequence; determining an emotion tag according to a target service data sequence, wherein the target service data sequence is the preprocessed service data within the observation window in the preprocessed service data sequence, and the emotion tag represents a risk control tendency for the virtual item; in response to determining that the emotion tag is a negative emotion tag, generating negative adjustment control policy information for the virtual item according to the current control policy information corresponding to the virtual item and the emotion tag as updated control policy information; in response to determining that the emotion tag is a positive emotion tag, generating positive adjustment control policy information for the virtual item according to the current control policy information and the emotion tag as updated control policy information; performing virtual item regulation on the virtual item according to the current control policy information or the updated control policy information, including: determining abnormal control information according to the current control policy information or the updated control policy information, the emotion tag, and an operation anomaly prediction model; in response to determining that the abnormal control information indicates a control anomaly in the current control policy information or the updated control policy information, determining a control instruction corresponding to the abnormal control information in an abnormal control decision tree; and locking a credit-granting device related to the virtual item or activating a firewall to block operations related to the virtual item according to the control instruction.

[0007] Second aspect, some embodiments of the present disclosure provide a virtual item operation device based on emotion tags. The device includes: an acquisition unit configured to acquire a real-time service data sequence for a virtual item; a data preprocessing unit configured to perform data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; a first determination unit configured to determine an observation window according to the preprocessed service data sequence; a second determination unit configured to determine an emotion tag for a target service data sequence, where the target service data sequence is the preprocessed service data within the observation window in the preprocessed service data sequence, and the emotion tag represents a risk control tendency for the virtual item; a first generation unit configured to, in response to determining that the emotion tag is a negative emotion tag, generate negative adjustment control strategy information for the virtual item according to the current control strategy information corresponding to the virtual item and the emotion tag as updated control strategy information; a second generation unit configured to, in response to determining that the emotion tag is a positive emotion tag, generate positive adjustment control strategy information for the virtual item according to the current control strategy information and the emotion tag as updated control strategy information; a virtual item regulation unit configured to regulate the virtual item according to the current control strategy information or the updated control strategy information, including: determining abnormal control information according to the current control strategy information or the updated control strategy information, the emotion tag, and an operation anomaly prediction model; determining a control instruction corresponding to the abnormal control information in an abnormal control decision tree in response to determining that the abnormal control information indicates a control anomaly in the current control strategy information or the updated control strategy information; and locking a credit-granting device related to the virtual item or activating a firewall to block operations related to the virtual item according to the control instruction.

[0008] Third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect above.

[0009] Fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, where the program, when executed by a processor, implements the method described in any implementation manner of the first aspect above.

[0010] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the method for operating virtual items based on emotion tags in some embodiments of the present disclosure, effective prevention and protection against abnormal operations are achieved, potential data risks are avoided, and device security is ensured. Specifically, the reason for the above problems is as follows: For frequent virtual item operations, using manual methods for abnormal control makes it difficult to comprehensively and effectively detect abnormal virtual item operations, and thus it is impossible to accurately and effectively perform corresponding control scheduling for virtual items. Especially when there are abnormal virtual item operations, it is impossible to effectively prevent and protect against abnormal operations, which may lead to data risks and device security risks. Based on this, in some embodiments of the present disclosure, the method for operating virtual items based on emotion tags first collects real-time service data sequences for virtual items to obtain real-time data for virtual items. Secondly, the above real-time service data sequences are preprocessed to obtain preprocessed service data sequences. Through data preprocessing, the data quality is improved, and the noise impact that low-quality data may have on subsequent results is eliminated. Then, an observation window is determined according to the above preprocessed service data sequences. In practice, the observation window is dynamically determined by combining the preprocessed service data sequences to facilitate the subsequent capture of abnormal control tendencies. Further, an emotion tag is determined according to the target service data sequence, where the target service data sequence is the preprocessed service data within the above observation window in the above preprocessed service data sequences, and the emotion tag represents the risk control tendency for the above virtual item. In this way, by combining the preprocessed service data within the observation window, the risk control tendency for the virtual item is quantified through the emotion tag. In addition, in response to determining that the above emotion tag is a negative emotion tag, according to the current control strategy information corresponding to the above virtual item and the above emotion tag, a negative adjustment control strategy information for the above virtual item is generated as the updated control strategy information. Immediately afterwards, in response to determining that the above emotion tag is a positive emotion tag, according to the above current control strategy information and the above emotion tag, a positive adjustment control strategy information for the above virtual item is generated as the updated control strategy information. In this way, the corresponding control strategy information is updated by combining the current control strategy information and the emotion tag. Finally, according to the above current control strategy information or the above updated control strategy information, virtual item regulation is performed on the above virtual item, including: determining abnormal control information according to the current control strategy information or the updated control strategy information, the emotion tag, and the operation anomaly prediction model; in response to determining that the abnormal control information indicates a control anomaly in the current control strategy information or the updated control strategy information, determining the control instruction corresponding to the abnormal control information in the abnormal control decision tree; and locking the credit-granting device related to the above virtual item or activating the firewall to block operations related to the virtual item according to the control instruction.In particular, for abnormal virtual item operations, the credit-granting device is locked or the firewall is activated to block virtual item-related operations. In this way, abnormal operations are effectively prevented and protected, potential data risks are avoided, and device security is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0012] Figure 1 is a flowchart of some embodiments of a method for virtual item operations based on emotion tags according to the present disclosure;

[0013] Figure 2 is a schematic diagram of the determination process of the target service data sequence;

[0014] Figure 3 is a schematic structural diagram of some embodiments of a virtual item operation device based on emotion tags according to the present disclosure;

[0015] Figure 4 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0017] In addition, it should be noted that for the sake of convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0018] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or mutual dependence relationship of the functions performed by these devices, modules, or units.

[0019] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly stated in the context, it should be understood as "one or more".

[0020] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are for illustrative purposes only and are not used to limit the scope of these messages or information.

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

[0022] Continuing to refer to Figure 1 , a flow 100 of some embodiments of a method for operating virtual items based on emotion tags according to the present disclosure is shown. The method for operating virtual items based on emotion tags includes the following steps:

[0023] Step 101, collecting a real-time service data sequence for a virtual item.

[0024] In some embodiments, the execution subject (e.g., a computing device) of the method for operating virtual items based on emotion tags can collect a real-time service data sequence for a virtual item through a wired connection or a wireless connection. Among them, the virtual item can be an item with a financial value attribute for which the corresponding control policy information is to be updated. In practice, the virtual item can be, but is not limited to: stocks, bonds, futures, funds, options, trust products, etc. In addition, the virtual item can also be a combination of products with different financial value attributes. The real-time service data sequence is time-series service data for the virtual item. In practice, the real-time service data can include, but is not limited to: opening price, closing price, highest price, lowest price. Optionally, the real-time service can also include metrics for measuring liquidity such as trading volume. Specifically, the above execution subject can collect, at a fixed time granularity, the service data generated in real time for the virtual item as the above real-time service data sequence. Among them, the fixed time granularity can be: any time granularity of second-level time granularity, millisecond-level time granularity, or minute-level time granularity.

[0025] It should be noted that the above wireless connection methods can include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future-developed wireless connection methods.

[0026] It should be noted that the above computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the above-listed hardware devices. It can be implemented as, for example, multiple software or software modules for providing distributed services, or can be implemented as a single software or software module. No specific limitation is made here.

[0027] Step 102, perform data preprocessing on the real-time service data sequence to obtain the preprocessed service data sequence.

[0028] In some embodiments, the above-mentioned execution entity may perform data preprocessing on the real-time service data sequence to obtain the preprocessed service data sequence. Among them, the preprocessed service data sequence may be the service data sequence obtained after data preprocessing.

[0029] In some optional implementation manners of some embodiments, the above-mentioned execution entity performs data preprocessing on the real-time service data sequence to obtain the preprocessed service data sequence, which may include the following steps:

[0030] First step, for each real-time service data in the above-mentioned real-time service data sequence, perform the following processing steps:

[0031] The first sub-step is to perform data validity verification on the above-mentioned real-time service data.

[0032] In practice, the above-mentioned execution entity may perform extreme value verification on the real-time service data. For example, through the corresponding valid value range, perform extreme value verification on the opening price, closing price, highest price, and lowest price included in the real-time service data. When it exceeds the valid value range, it is characterized as passing the extreme value verification.

[0033] The second sub-step is to, in response to determining that the above-mentioned real-time service data passes the validity verification, perform data cleaning on the above-mentioned real-time service data to obtain the cleaned service data.

[0034] In practice, the above-mentioned execution entity may perform data cleaning on the real-time service data in ways including but not limited to: removing missing values, removing duplicate data, etc., so as to perform data cleaning on the real-time service data and obtain the cleaned service data.

[0035] The third sub-step is to perform data formatting processing on the above-mentioned cleaned service data to obtain the formatted service data.

[0036] In practice, the above-mentioned execution entity may perform data formatting processing on the cleaned service data according to a preset data storage format to obtain the formatted service data. For example, convert the cleaned service data into JSON (JavaScript Object Notation) format to obtain the formatted service data.

[0037] Second step, determine the data granularity corresponding to the above-mentioned real-time service data sequence.

[0038] Among them, the above data granularity characterizes the data collection frequency corresponding to the above real-time service data sequence. In practice, the data collection frequency can characterize any one of the time granularities of second-level time granularity, millisecond-level time granularity, and minute-level time granularity. Specifically, by determining the collection time interval between adjacent real-time service data, the above data granularity can be determined.

[0039] In the third step, in response to determining that the above data granularity is not the preset data granularity and the above data granularity is less than the above preset data granularity, downsample the obtained formatted service data sequence with the above preset data granularity to obtain the above preprocessed service data sequence.

[0040] Among them, the preset data granularity can characterize the minute-level time granularity.

[0041] As an example, the formatted service data sequence may include: [Formatted service data sequence A1,..., Formatted service data sequence A60,..., Formatted service data sequence A120,..., Formatted service data sequence A180,..., Formatted service data sequence A240]. The preprocessed service data sequence obtained by downsampling the formatted service data sequence may be [Formatted service data sequence A1, Formatted service data sequence A60, Formatted service data sequence A120, Formatted service data sequence A180, Formatted service data sequence A240].

[0042] Step 103, determine an observation window according to the preprocessed service data sequence.

[0043] In some embodiments, the above execution subject may determine an observation window according to the preprocessed service data sequence. Among them, the observation window may be a time window for determining emotion labels. By determining the observation window, further data downsampling can be performed, and at the same time, it is possible to focus on representative service data.

[0044] In some optional implementation manners of some embodiments, the above execution subject determines an observation window according to the preprocessed service data sequence, which may include the following steps:

[0045] In the first step, initialize the window length corresponding to the above observation window to obtain an initial observation window.

[0046] Among them, the window length of the above initial observation window is the initial window length. The window length characterizes the number of preprocessed service data that can be included in the initial observation window.

[0047] In the second step, according to the initialized window length and the above preprocessed service data sequence, perform the following observation window determination steps:

[0048] The first sub-step is to determine the target business data sequence.

[0049] Among them, the target business data in the target business data sequence is the preprocessed business data in the above-mentioned preprocessed business data sequence within the initial observation window.

[0050] As an example, refer to Figure 2 the schematic diagram of the determination process of the target business data sequence shown in the figure. Among them, the above-mentioned execution entity can use at least one preprocessed business data within the initial observation window 202 in the preprocessed business data sequence 201 as the target business data sequence 203.

[0051] The second sub-step is to determine the business data mean value according to the target business data sequence.

[0052] In practice, the above-mentioned execution entity can determine the business data mean value according to the target business data sequence through the following formula:

[0053]

[0054] Among them, is the business data mean value. i represents the serial number, and w k represents the window length of the initial observation window. R i represents the closing price included in the i-th target business data in the target business data sequence.

[0055] The third sub-step is to determine the window characteristic value of the initial observation window according to the target business data sequence, the business data mean value, the first target business data, and the second target business data.

[0056] Among them, the first target business data is the target business data corresponding to the maximum value in the target business data sequence. The second target business data is the target business data corresponding to the minimum value in the target business data sequence.

[0057] In practice, the above-mentioned execution entity can determine the window characteristic value of the initial observation window through the following formula according to the target business data sequence, the business data mean value, the first target business data, and the second target business data:

[0058]

[0059] Among them, f(w k ) represents the window characteristic value. is the business data mean value. i represents the serial number, and w k represents the window length of the initial observation window. R i represents the closing price included in the i-th target business data in the target business data sequence. R maxIt is the opening price included in the first target business data. R min It is the opening price included in the second target business data. Among them, the value range of the window length of the initial observation window is [w 0 , w 1 . Among them, w 0 represents the minimum window length of the initial observation window. W 1 represents the maximum window length of the initial observation window. In practice, the value range of the window length of the initial observation window varies according to different scenarios. For example, for general virtual items of futures or securities types, the value range can be [15, 30].

[0060] The fourth sub-step, in response to determining that the mean value of the business data is greater than or equal to the preset threshold, determines the initial observation window as the above-mentioned observation window.

[0061] Among them, the preset threshold dynamically changes according to the business scenario corresponding to the above virtual item. In practice, for scenarios with large fluctuations in business data, a larger preset threshold can be taken, and accordingly, the window length of the observation window is increased, so that the fluctuations of the business data can be better observed within the observation window. For scenarios with small fluctuations in business data, a smaller preset threshold can be taken, and accordingly, the window length of the observation window is reduced, so that the business data with low change amplitude is reduced and included in the observation window, reducing the data processing volume. Specifically, the preset threshold can be obtained through test simulation based on historical business data. For example, the preset threshold can be set between 50 and 70 according to empirical values. And test by substituting historical business data within this range (50 - 70). In order to improve the determination speed of the preset threshold, the dichotomy method can be used to determine the preset threshold.

[0062] The third step, in response to determining that the mean value of the business data is less than the above preset threshold, increments the window length of the initial observation window to obtain an observation window with an increased window length, which is used as the initial observation window, and then executes the above observation window determination step again.

[0063] In practice, the above execution subject can increment the window length of the initial observation window by 1 to obtain an observation window with an increased window length, which is used as the initial observation window.

[0064] Step 104, determine the sentiment label according to the target business data sequence.

[0065] In some embodiments, the above-mentioned execution entity may determine an emotion label according to the target service data sequence. Among them, the emotion label represents the risk control tendency for the above-mentioned virtual item. In practice, the label values of the emotion label may include: 1, 0, -1. Among them, when the emotion label is "1", it is a negative emotion label, indicating that risk control needs to be carried out on the virtual item. When the emotion label is "0", it is a neutral emotion label, indicating that it is impossible to effectively judge whether risk control is required. When the emotion label is "1", it is a positive emotion label, indicating that the risk control of the virtual item needs to be relaxed.

[0066] In some optional implementation manners of some embodiments, the above-mentioned execution entity determines an emotion label according to the target service data sequence, including:

[0067] First step, for each target service data in the above-mentioned target service data sequence, determine the average service data corresponding to the above-mentioned target service data according to the above-mentioned target service mutual data.

[0068] Among them, the average service data refers to the average of the opening price, closing price, highest price, and lowest price included in the target service data.

[0069] Second step, determine the first emotion value and the second emotion value respectively according to the obtained average service data sequence.

[0070] In practice, the above-mentioned execution entity may determine the first emotion value according to the obtained average service data sequence through the following formula:

[0071]

[0072] Among them, mkt_d represents the first emotion value. Specifically, since when the average service data is greater than or equal to the preset threshold, the initial observation window is the above-mentioned observation window, so W k represents the window length of the observation window. i represents the serial number. df[i] represents the i-th average service data in the average service data sequence. df[i - 1] represents the (i - 1)-th average service data in the average service data sequence. df[0:i] represents the average of the 0th average service data to the i-th average service data in the average service data sequence. max(df[0:i]) represents the largest average service data among the 0th average service data to the l-th average service data in the average service data sequence.

[0073] In practice, the above-mentioned execution entity may determine the second emotion value according to the obtained average service data sequence through the following formula:

[0074]

[0075] Among them, mkt_vd represents the first emotion value. Specifically, since when the mean value of business data is greater than or equal to the preset threshold, the initial observation window is the above-mentioned observation window, so W k represents the window length of the observation window. i represents the serial number. df[i] represents the i-th mean business data in the mean business data sequence. df[i - 1] represents the (i - 1)-th mean business data in the mean business data sequence. df[0:i] represents the mean of the 0th mean business data to the i-th mean business data in the mean business data sequence. min(df[0:i]) represents the smallest mean business data among the 0th mean business data to the i-th mean business data in the mean business data sequence.

[0076] Optionally, the above-mentioned execution entity can also determine the first emotion value according to the obtained mean business data sequence through the following formula:

[0077]

[0078] Among them, mkt_d represents the first emotion value. Specifically, since when the mean value of business data is greater than or equal to the preset threshold, the initial observation window is the above-mentioned observation window, so W k represents the window length of the observation window. i represents the serial number. df[i] represents the i-th mean business data in the mean business data sequence. df[i - 1] represents the (i - 1)-th mean business data in the mean business data sequence. df[0:i] represents the mean of the 0th mean business data to the i-th mean business data in the mean business data sequence. max(df[0:i]) represents the largest mean business data among the 0th mean business data to the i-th mean business data in the mean business data sequence. ewa() represents the exponentially weighted average.

[0079] Optionally, the above-mentioned execution entity can also determine the second emotion value according to the obtained mean business data sequence through the following formula:

[0080]

[0081] Among them, mkt_vd represents the first emotion value. Specifically, since when the mean value of business data is greater than or equal to the preset threshold, the initial observation window is the above-mentioned observation window, so W kRepresents the window length of the observation window. i represents the serial number. df[i] represents the i-th mean service data in the mean service data sequence. df[i - 1] represents the (i - 1)-th mean service data in the mean service data sequence. df[0:i] represents the mean of the 0-th mean service data to the i-th mean service data in the mean service data sequence. min(df[0:i]) represents the smallest mean service data among the mean of the 0-th mean service data to the i-th mean service data in the mean service data sequence. ewa() represents the exponentially weighted average.

[0082] In the third step, determine the target emotion value as the smallest emotion value among the above first emotion value and the above second emotion value.

[0083] In practice, the determination process of the target emotion value can be characterized by the following formula:

[0084] mkt = min(mkt_d, mkt_vd)

[0085] Among them, mkt represents the target emotion value. mkt_d represents the first emotion value. mkt_vd represents the second emotion value.

[0086] In the fourth step, determine the mean emotion value, extreme emotion value, and average emotion value within the preset time period.

[0087] Among them, the above preset time period is a time period prior to the acquisition time corresponding to the above real-time service data sequence. The above extreme emotion value is the minimum value of the emotion values within the preset time period. The above mean emotion value is the average value of the emotion values within the preset time period. Optionally, the mean emotion value can also represent the median value of the emotion values within the preset time period. Specifically, the preset time period can be the past 30 days.

[0088] In the fifth step, in response to determining that the above target emotion value is less than the above mean emotion value, determine the first emotion tendency probability according to the above mean emotion value, the above target emotion value, the above extreme emotion value, and the above second extreme emotion value.

[0089] In the sixth step, in response to determining that the above target emotion value is greater than or equal to the above mean emotion value, determine the preset emotion tendency probability as the first emotion tendency probability.

[0090] Among them, the preset emotion tendency probability is 0.

[0091] In practice, the first emotion tendency probability can be determined by the following formula:

[0092]

[0093] Among them, rt represents the first emotion tendency probability. mkt represents the target emotion value. mktmin Represents the value of the sentiment value. mkt the Represents the average sentiment value.

[0094] Optionally, determining the sentiment label according to the target business data sequence as described above further includes:

[0095] First step, determine the second sentiment tendency probability.

[0096] In practice, the above-mentioned execution entity can re-execute the steps in step 101 to step 104 at a specific time after the acquisition time of the real-time business data sequence to obtain the second sentiment tendency probability. Among them, the calculation method of the second sentiment tendency probability is the same as the determination method of the first sentiment tendency probability.

[0097] Second step, perform weighted correction according to the above-mentioned first sentiment tendency probability and the above-mentioned second sentiment tendency probability to obtain the corrected sentiment tendency probability.

[0098] In practice, the above-mentioned execution entity can perform weighted correction according to the above-mentioned first sentiment tendency probability and the above-mentioned second sentiment tendency probability through the following formula to obtain the corrected sentiment tendency probability:

[0099] rt_rev = q·rt + (1 - q)·rt_2

[0100] Where, rt_rev represents the corrected sentiment tendency probability. rt represents the first sentiment tendency probability. rt_2 represents the second sentiment tendency probability. q represents the weight corresponding to the first sentiment tendency probability. In practice, the value range of the weight corresponding to the first sentiment tendency probability is 0.3 to 0.5.

[0101] By determining the corrected sentiment tendency probability, the correction of the first sentiment tendency probability is achieved. In addition, the calculation of the sentiment tendency probability can be carried out in time periods. For example, a single trading day can be divided into 3 time intervals (morning, afternoon, and night) to calculate the sentiment tendency probability respectively.

[0102] Third step, determine the above-mentioned sentiment label according to the above-mentioned first sentiment tendency probability or the above-mentioned corrected sentiment tendency probability:

[0103] In practice, when no weighted correction is performed, the above-mentioned sentiment label can be determined according to the first sentiment tendency probability through the following formula:

[0104]

[0105] Where, flag represents the sentiment label. rt represents the first sentiment tendency probability. r i Represents the last target business data (including the closing price) within the observation window. r i+1Represents the first target business data (including the closing price) after the observation window.

[0106] In practice, when performing weighted correction, the above-mentioned emotion labels can be determined according to the emotion tendency probability after correction through the following formula:

[0107]

[0108] Among them, flag represents the emotion label. rt_rev represents the emotion tendency probability after correction. r i Represents the last target business data (including the closing price) within the observation window. r i+1 Represents the first target business data (including the closing price) after the observation window.

[0109] Step 105, in response to determining that the emotion label is a negative emotion label, generate negative adjustment control strategy information for the virtual item according to the current control strategy information corresponding to the virtual item and the emotion label, as the updated control strategy information.

[0110] In some embodiments, in response to determining that the emotion label is a negative emotion label, the above-mentioned execution entity can generate negative adjustment control strategy information for the virtual item according to the current control strategy information corresponding to the virtual item and the emotion label, as the updated control strategy information. Among them, when the label value of the emotion label is "-1", it is a negative emotion label. The current control strategy information represents the current item control strategy for the virtual item. Specifically, the current control strategy information includes but is not limited to: the current position, the margin ratio, the virtual item proportion configuration, the minimum position, and the maximum position.

[0111] As an example, the above-mentioned execution entity can generate negative adjustment control strategy information for the virtual item according to the preset control strategy rules, according to the current control strategy information corresponding to the virtual item and the emotion label, as the updated control strategy information. Among them, the control strategy rule is a trigger rule for the change of the regulation control strategy pre-constructed for different scenarios.

[0112] Optionally, the above-mentioned execution entity can generate updated control policy information according to the current control policy information and emotion tags through a control policy information generation model. Specifically, the control policy information model includes: a global feature library, a control policy information feature extraction model, and a control policy information prediction model. Among them, the control policy information feature extraction model and the control policy information prediction model adopt an encoder-decoder network model. Among them, the control policy information feature extraction model is used to extract features from the current control policy information. The control policy information prediction model is used to generate updated control policy information. Specifically, when the emotion tag is a negative emotion tag, it will constrain the risk control tendency corresponding to the generated updated control policy information to be higher than the risk control tendency corresponding to the current control policy information. In addition, in order to avoid the situation of falling into a local solution that may occur when only relying on the updated control policy information of the current virtual item operation. Therefore, a global feature library is introduced. Among them, the global feature library is constructed based on expert experience and is used to store the features corresponding to the real-time domain change situation in the field where the virtual item is located. The decoding network model takes the input of the control policy information feature extraction model as a local constraint and the features corresponding to the real-time domain change situation in the field where the virtual item is located in the global feature library as a global constraint, so as to obtain the updated control policy information. In addition, considering that the global features can be obtained by combining multiple data sources, therefore, the global features are constructed by using a multi-modal model for corresponding feature extraction. Among them, the multi-modal model can include: a text feature extraction module, an image feature extraction module, a video feature extraction module, and an alignment layer for aligning the output features of the text feature extraction module, the image feature extraction module, and the video feature extraction module. In practice, the text feature extraction module can adopt the Seq2Seq model structure. In addition, since a video can be understood as a series of consecutive frames of images, the video feature extraction module and the image feature extraction module can share the model structure. Specifically, the Video-LLaMa model can be used to understand the content of images and videos to output image features or video features for videos or images. In addition, considering that the features output by different modules may be in different feature spaces, an alignment layer is used to align the features output by the text feature extraction module, the image feature extraction module, and the video feature extraction module to map the features to the same or similar feature spaces. Through the above control policy information generation model, corresponding control policies can be automatically generated on the premise of known emotion tags, especially for virtual items with complex configurations, improving the generation efficiency and accuracy of control policy information. In practice, for virtual item operations, when there is an incorrect virtual item regulation, such as when there is no abnormality in the virtual item operation, but the credit-granting device is locked or the firewall is activated incorrectly, it may affect the normal use of the device.Therefore, based on the precisely generated control strategy information, the present disclosure can achieve precise and effective regulation of virtual items, especially for abnormal virtual item operations such as locking credit devices or activating firewalls.

[0113] Step 106, in response to determining that the emotion label is a positive emotion label, generate positive regulation control strategy information for the virtual item based on the current control strategy information and the emotion label, as the updated control strategy information.

[0114] In some embodiments, in response to determining that the emotion label is a positive emotion label, the above-mentioned execution entity can generate positive regulation control strategy information for the virtual item based on the current control strategy information and the emotion label, as the updated control strategy information.

[0115] As an example, the above-mentioned execution entity can generate negative regulation control strategy information for the virtual item based on the preset control strategy rules, the current control strategy information corresponding to the virtual item, and the emotion label, as the updated control strategy information. Among them, the control strategy rules are pre-constructed trigger rules for the change of the regulation control strategy in different scenarios.

[0116] Optionally, when the emotion label is a positive emotion label, it is restricted that the risk control tendency corresponding to the generated updated control strategy information is lower than the risk control tendency corresponding to the current control strategy information.

[0117] Step 107, perform virtual item regulation on the virtual item according to the current control strategy information or the updated control strategy information.

[0118] In some embodiments, the above-mentioned execution entity can perform virtual item regulation on the virtual item according to the current control strategy information or the updated control strategy information. Specifically, when there is updated control strategy information, the updated control strategy information can be preferentially executed to perform virtual item regulation on the virtual item. When there is no updated control strategy information, the current control strategy information can be continued to be executed to perform virtual item regulation on the virtual item. Specifically, the above-mentioned execution entity can make corresponding adjustments to the current holding quantity, margin ratio, and virtual item proportion configuration corresponding to the virtual item according to the current control strategy information or the updated control strategy information, so as to achieve the purpose of virtual item regulation on the virtual item.

[0119] As an example, the above-mentioned execution entity performs virtual item regulation on the virtual item according to the current control strategy information or the updated control strategy information, including:

[0120] First step, determine abnormal control information according to the above-mentioned current control strategy information or the above-mentioned updated control strategy information, the above-mentioned emotion label, and the operation anomaly prediction model.

[0121] Among them, the abnormal control information includes: abnormal type and abnormal probability. The abnormal type characterizes the possible abnormal types that may occur when executing the current control policy information or the updated control policy information. The abnormal probability characterizes the occurrence probability of the abnormal type. The operation abnormal prediction model includes: a control policy information feature extraction model and an abnormal prediction layer. In practice, the encoding network included in the above virtual item operation model can be reused to extract features from the current control policy information or the updated control policy information to generate control information features, thereby reducing the model size. Then, the above execution entity can input the control information features into the above abnormal prediction layer to obtain the abnormal type and the abnormal probability corresponding to the abnormal type. In practice, the abnormal prediction layer can be implemented using a fully connected layer. Specifically, in the training phase, the abnormal prediction model is trained in a supervised training manner, and the training samples are selected from the historical control policy information marked with the corresponding abnormal types, and the corresponding training labels are the abnormal types corresponding to the historical control policy information.

[0122] In the second step, in response to determining that the above abnormal control information indicates a control abnormality in the current control policy information or the updated control policy information, determine the control instruction corresponding to the above abnormal control information in the abnormal control decision tree.

[0123] Among them, the abnormal control decision tree is a decision tree that records different abnormal types and the corresponding control instructions. The control instruction characterizes the instruction related to the abnormal control of the virtual item.

[0124] In the third step, according to the above control instruction, lock the credit-granting device related to the above virtual item, or activate the firewall to block the operations related to the virtual item.

[0125] As an example, the control instruction can be a virtual item data locking instruction, that is, lock the business data related to the virtual item to prevent the data from being tampered with.

[0126] As another example, the control instruction can be the locking of the credit-granting device related to the virtual item. Among them, the credit-granting device can be an authorized mobile terminal. By locking the credit-granting device, it is impossible to execute the operations related to the virtual item through the credit-granting device, so as to avoid the corresponding abnormal operations and the possible data abnormalities.

[0127] As still another example, the control instruction can be a data leakage prevention and control instruction for the data storage device related to the virtual item. For example, when unauthorized or highly abnormal data modification, deletion, etc. occur for the business data related to the virtual item, the firewall can be activated to block the operations related to the virtual item. In this way, abnormal operations can be blocked.

[0128] Optionally, when the exception control information indicates that there is no control exception in the current control policy information or the updated control policy information, execute the current control policy information or the updated control policy information to perform virtual item regulation on the virtual item.

[0129] In some alternative implementation manners of some embodiments, the above-mentioned execution subject performing virtual item regulation on the virtual item according to the current control policy information or the updated control policy information may include the following steps:

[0130] First, generate regulation prompt information for the above-mentioned virtual item according to the above-mentioned current control policy information or the above-mentioned updated control policy information.

[0131] In practice, when corresponding regulation of the virtual item is required, it is necessary to notify the corresponding processing personnel for regulation confirmation. Therefore, regulation prompt information related to the virtual item can be generated.

[0132] Second, send the above-mentioned regulation prompt information to the target terminal.

[0133] Among them, the above-mentioned target terminal is the terminal bound to the processing object account associated with the above-mentioned virtual item regulation. In practice, the sending of the regulation prompt information can be transmitted in an encrypted manner.

[0134] Third, in response to receiving the regulation confirmation instruction initiated by the above-mentioned target terminal, execute the above-mentioned current control policy information or the above-mentioned updated control policy information.

[0135] In practice, by adding steps of manual review and confirmation before execution, the problem of possible regulation errors in automatic execution is avoided, and the security guarantee during the regulation process is increased.

[0136] Fourth, in response to receiving the regulation update instruction initiated by the above-mentioned target terminal, update the above-mentioned current control policy information or the above-mentioned updated control policy information according to the above-mentioned regulation update instruction to obtain the secondarily updated control policy information or the tertiarily updated control policy information.

[0137] In practice, the regulation update instruction may be an adjustment item initiated by the processing object associated with the above-mentioned virtual item regulation for the current control policy information or the updated control policy information. Specifically, when the regulation update instruction is for the current control policy information, the current control policy information can be updated according to the regulation update quality to obtain the secondarily updated control policy information. When the regulation update instruction is for the updated control policy information, the updated control policy information can be updated according to the regulation update quality to obtain the tertiarily updated control policy information.

[0138] Fourthly, according to the above-mentioned control policy information after the second update or the above-mentioned control policy information after the third update, perform virtual item regulation on the above-mentioned virtual item.

[0139] In practice, the above-mentioned execution entity may execute the above-mentioned control policy information after the second update or the above-mentioned control policy information after the third update to perform virtual item regulation on the above-mentioned virtual item.

[0140] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the method for operating virtual items based on emotion tags in some embodiments of the present disclosure, effective prevention and protection against abnormal operations are achieved, potential data risks are avoided, and device security is ensured. Specifically, the reason for the above problems is that for frequent virtual item operations, it is difficult to comprehensively and effectively detect abnormal virtual item operations by manual means such as artificial methods, and thus it is impossible to accurately and effectively perform corresponding control and scheduling on virtual items. Especially when there are abnormal virtual item operations, it is impossible to effectively prevent and protect against abnormal operations, which may result in data risks and device security risks. Based on this, in some embodiments of the present disclosure, the method for operating virtual items based on emotion tags first collects a real-time service data sequence for the virtual item to obtain real-time data for the virtual item. Secondly, the real-time service data sequence is preprocessed to obtain a preprocessed service data sequence. Through data preprocessing, the data quality is improved, and the noise impact that low-quality data may have on subsequent results is eliminated. Then, an observation window is determined based on the preprocessed service data sequence. In practice, the observation window is dynamically determined by combining the preprocessed service data sequence to facilitate the subsequent capture of abnormal control tendencies. Further, an emotion tag is determined based on the target service data sequence, where the target service data sequence is the preprocessed service data within the observation window in the preprocessed service data sequence, and the emotion tag represents the risk control tendency for the virtual item. In this way, by combining the preprocessed service data within the observation window, the risk control tendency for the virtual item is quantified through the emotion tag. In addition, in response to determining that the emotion tag is a negative emotion tag, a negative adjustment control strategy information for the virtual item is generated based on the current control strategy information corresponding to the virtual item and the emotion tag as the updated control strategy information. Immediately afterwards, in response to determining that the emotion tag is a positive emotion tag, a positive adjustment control strategy information for the virtual item is generated based on the current control strategy information and the emotion tag as the updated control strategy information. In this way, the corresponding control strategy information is updated by combining the current control strategy information and the emotion tag. Finally, the virtual item is regulated according to the current control strategy information or the updated control strategy information, including: determining abnormal control information based on the current control strategy information or the updated control strategy information, the emotion tag, and the operation anomaly prediction model; when it is determined that the abnormal control information indicates a control anomaly in the current control strategy information or the updated control strategy information, determining a control instruction corresponding to the abnormal control information in the abnormal control decision tree; and locking the credit-granting device related to the virtual item or activating the firewall to block operations related to the virtual item according to the control instruction.In particular, for abnormal virtual item operations, the credit-granting device is locked or the firewall is activated to block virtual item-related operations. In this way, abnormal operations are effectively prevented and protected, potential data risks are avoided, and device security is ensured.

[0141] Further reference Figure 3 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a virtual item operation device based on emotion tags. These device embodiments correspond to Figure 1 the method embodiments shown, and the virtual item operation device based on emotion tags can be specifically applied to various electronic devices.

[0142] Such as Figure 3As shown in the figure, the virtual item operation device 300 based on emotion tags in some embodiments includes: a collection unit 301, a data preprocessing unit 302, a first determination unit 303, a second determination unit 304, a first generation unit 305, a second generation unit 306, and a virtual item scheduling unit 307. The collection unit 301 is configured to collect a real-time service data sequence for the virtual item; the data preprocessing unit 302 is configured to perform data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; the first determination unit 303 is configured to determine an observation window according to the preprocessed service data sequence; the second determination unit 304 is configured to determine an emotion tag for the target service data sequence, where the target service data sequence is the preprocessed service data within the observation window in the preprocessed service data sequence, and the emotion tag represents the risk control tendency for the virtual item; the first generation unit 305 is configured to, in response to determining that the emotion tag is a negative emotion tag, generate negative adjustment control policy information for the virtual item according to the current control policy information corresponding to the virtual item and the emotion tag as the updated control policy information; the second generation unit 306 is configured to, in response to determining that the emotion tag is a positive emotion tag, generate positive adjustment control policy information for the virtual item according to the current control policy information and the emotion tag as the updated control policy information; the virtual item control unit 307 is configured to perform virtual item control on the virtual item according to the current control policy information or the updated control policy information, including: determining abnormal control information according to the current control policy information or the updated control policy information, the emotion tag, and the operation anomaly prediction model; in response to determining that the abnormal control information indicates a control anomaly in the current control policy information or the updated control policy information, determining a control instruction corresponding to the abnormal control information in the abnormal control decision tree; and locking the credit-granting device related to the virtual item or activating a firewall to block operations related to the virtual item according to the control instruction.

[0143] It can be understood that the units described in the virtual item operation device 300 based on emotion tags correspond to the respective steps in the method described in the reference Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the virtual item operation device 300 based on emotion tags and the units included therein, and will not be elaborated here.

[0144] Next, refer to Figure 4 , which shows a schematic structural diagram of an electronic device (e.g., a computing device) 400 suitable for implementing some embodiments of the present disclosure. Figure 4The electronic device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0145] As Figure 4 shown, the electronic device 400 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in the read-only memory 402 or a program loaded from the storage device 408 into the random access memory 403. In the random access memory 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the read-only memory 402, and the random access memory 403 are connected to each other through a bus 404. The input / output interface 405 is also connected to the bus 404.

[0146] Generally, the following devices may be connected to the input / output interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 4 the electronic device 400 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be implemented or had alternatively. Figure 4 Each block shown in

[0147] particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the method shown in the flowchart. In such some embodiments, the computer program may be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the read-only memory 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0148] It should be noted that the computer-readable media described in some embodiments of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0149] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0150] The above computer-readable medium may be included in the above electronic device; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is caused to: collect a real-time service data sequence for a virtual item; perform data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; determine an observation window according to the preprocessed service data sequence; determine an emotion label according to a target service data sequence, where the target service data sequence is the preprocessed service data within the observation window in the preprocessed service data sequence, and the emotion label represents a risk control tendency for the virtual item; in response to determining that the emotion label is a negative emotion label, generate negative adjustment control strategy information for the virtual item according to the current control strategy information corresponding to the virtual item and the emotion label as updated control strategy information; in response to determining that the emotion label is a positive emotion label, generate positive adjustment control strategy information for the virtual item according to the current control strategy information and the emotion label as updated control strategy information; perform virtual item regulation on the virtual item according to the current control strategy information or the updated control strategy information, including: determining abnormal control information according to the current control strategy information or the updated control strategy information, and the emotion label and an operation anomaly prediction model; in response to determining that the abnormal control information indicates a control anomaly in the current control strategy information or the updated control strategy information, determining a control instruction corresponding to the abnormal control information in an abnormal control decision tree; and locking a credit-granting device related to the virtual item or activating a firewall to block operations related to the virtual item according to the control instruction.

[0151] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0153] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes an acquisition unit, a data preprocessing unit, a first determination unit, a second determination unit, a first generation unit, a second generation unit, and a virtual item scheduling unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the second generation unit can also be described as "a unit that generates positive adjustment control policy information for the virtual item as updated control policy information according to the current control policy information and the emotion label in response to determining that the emotion label is a positive emotion label".

[0154] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0155] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. A virtual item operation method based on emotion tags, applied to a credit device or a firewall, comprising: Collect real-time business data sequences for virtual items; Performing data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; Determining an observation window according to the preprocessed business data sequence; Determining an emotion label according to a target business data sequence, wherein the target business data sequence is pre-processed business data in the pre-processed business data sequence and located within the observation window, and the emotion label represents a risk control tendency for the virtual item; In response to determining that the emotion tag is a negative emotion tag, generating negative adjustment control strategy information for the virtual item according to the current control strategy information corresponding to the virtual item and the emotion tag as updated control strategy information; In response to determining that the emotion tag is a positive emotion tag, generating positive adjustment control strategy information for the virtual item according to the current control strategy information and the emotion tag as updated control strategy information; According to the current control strategy information or the updated control strategy information, the virtual item is regulated, including: Determine abnormal control information according to the current control strategy information or the updated control strategy information, as well as the emotion label and the abnormal operation prediction model; In response to determining that the abnormal control information indicates that the current control strategy information or the updated control strategy information has a control abnormality, determining a control instruction corresponding to the abnormal control information in the abnormal control decision tree; According to the control instruction, the credit device related to the virtual item is locked, or a firewall is activated to shield the operations related to the virtual item.

2. The method according to claim 1, wherein: The performing data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence includes: For each real-time service data in the real-time service data sequence, the following processing steps are performed: Performing data validity verification on the real-time business data; In response to determining that the real-time business data passes the validity check, performing data cleansing on the real-time business data to obtain cleansed business data; Performing data formatting processing on the cleaned business data to obtain formatted business data; Determine a data granularity corresponding to the real-time service data sequence, wherein the data granularity represents a data collection frequency corresponding to the real-time service data sequence; In response to determining that the data granularity is not a preset data granularity and the data granularity is smaller than the preset data granularity, the obtained formatted business data sequence is downsampled at the preset data granularity to obtain the preprocessed business data sequence.

3. The method according to claim 2, wherein: The step of determining the observation window according to the preprocessed service data sequence includes: Initializing a window length corresponding to the observation window to obtain an initial observation window, wherein the window length of the initial observation window is an initial window length; According to the initialization window length and the pre-processed service data sequence, the following observation window determination steps are performed: Determining a target service data sequence, wherein the target service data in the target service data sequence is the preprocessed service data in the preprocessed service data sequence that is located within the initial observation window; Determine the mean of business data according to the target business data sequence; Determine the window characteristic value of the initial observation window according to the target business data sequence, the business data mean, the first target business data and the second target business data, wherein the first target business data is the target business data corresponding to the maximum value in the target business data sequence, and the second target business data is the target business data corresponding to the minimum value in the target business data sequence; In response to determining that the mean of the business data is greater than or equal to a preset threshold, determining an initial observation window as the observation window, wherein the preset threshold changes dynamically according to a business scenario corresponding to the virtual item; In response to determining that the mean value of the business data is less than the preset threshold, the window length of the initial observation window is incremented to obtain an observation window with incremented window length as the initial observation window, and the observation window determination step is performed again.

4. The method according to claim 3, wherein: Determining the emotion label according to the target business data sequence includes: For each target service data in the target service data sequence, determining the mean service data corresponding to the target service data according to the target service data; Determine the first emotion value and the second emotion value respectively according to the obtained mean business data sequence; Determine the smallest emotion value between the first emotion value and the second emotion value as the target emotion value; Determine a mean emotion value, an extreme emotion value, and a mean emotion value within a preset time period, wherein the preset time period is a time period prior to the collection time corresponding to the real-time business data sequence, the extreme emotion value is the minimum value of the emotion value within the preset time period, and the mean emotion value is the mean value of the emotion value within the preset time period; In response to determining that the target emotion value is less than the mean emotion value, determining a first emotion tendency probability according to the mean emotion value, the target emotion value, the first extreme emotion value, and the second extreme emotion value; In response to determining that the target emotion value is greater than or equal to the mean emotion value, a preset emotion tendency probability is determined as a first emotion tendency probability, wherein the preset emotion tendency probability is 0.

5. The method according to claim 4, wherein: The step of determining the emotion label according to the target business data sequence further includes: Determining the probability of a second emotional tendency; Performing weighted correction according to the first emotion tendency probability and the second emotion tendency probability to obtain a corrected emotion tendency probability; The emotion label is determined according to the first emotion tendency probability or the corrected emotion tendency probability.

6. The method according to claim 5, wherein: The step of regulating the virtual item according to the current control strategy information or the updated control strategy information includes: Generate control prompt information for the virtual item according to the current control strategy information or the updated control strategy information; Sending the control prompt information to a target terminal, wherein the target terminal is a terminal bound to a processing target account associated with the virtual item control; In response to receiving a control confirmation instruction initiated by the target terminal, executing the current control strategy information or the updated control strategy information; In response to receiving a control update instruction initiated by the target terminal, the current control strategy information or the updated control strategy information is updated according to the control update instruction to obtain the second updated control strategy information or the third updated control strategy information; The virtual item is regulated according to the control strategy information after the second update or the control strategy information after the third update.

7. A virtual item operation device based on emotion tags, applied to a credit device or a firewall, comprising: A collection unit, configured to collect a real-time business data sequence for virtual items; A data preprocessing unit, configured to perform data preprocessing on the real-time service data sequence to obtain a preprocessed service data sequence; A first determining unit is configured to determine an observation window according to the preprocessed service data sequence; A second determining unit is configured to determine a target business data sequence, wherein the target business data sequence is pre-processed business data in the pre-processed business data sequence and located within the observation window, and the emotion label represents a risk control tendency for the virtual item; A first generating unit is configured to generate negative adjustment control strategy information for the virtual item as updated control strategy information according to current control strategy information corresponding to the virtual item and the emotion tag in response to determining that the emotion tag is a negative emotion tag; A second generating unit is configured to generate positive adjustment control strategy information for the virtual item as updated control strategy information according to the current control strategy information and the emotion tag in response to determining that the emotion tag is a positive emotion tag; The virtual item regulation unit is configured to perform virtual item regulation on the virtual item according to the current control strategy information or the updated control strategy information, including: Determine abnormal control information according to the current control strategy information or the updated control strategy information, as well as the emotion label and the abnormal operation prediction model; In response to determining that the abnormal control information indicates that the current control strategy information or the updated control strategy information has a control abnormality, determining a control instruction corresponding to the abnormal control information in the abnormal control decision tree; According to the control instruction, the credit device related to the virtual item is locked, or a firewall is activated to shield the operations related to the virtual item.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images