People relation network-oriented relation inference method

Abstract

The invention discloses a relation inference method oriented to a character relation network, and particularly relates to the technical field of college platforms, inference operation data of a system corresponding to relation inference oriented to the character relation network are obtained, an inference error coefficient is obtained according to the inference operation data, and the inference error coefficient is compared with a preset threshold value; when the inference error coefficient is smaller than a preset threshold value, recording the inference error coefficient as an error signal, establishing a data set for the inference error coefficient corresponding to the error signal, calculating a standard deviation of the data set, comparing the standard deviation with the preset threshold value, and when the standard deviation is not smaller than the preset threshold value, giving an alarm by an alarm system. When a system of the relation inference method oriented to the character relation network has a problem, an alarm is given in time to remind a worker of timely maintenance, so that the relation inference result of students, faculty and employees and other related personnel of colleges is accurate or invalid, and the efficiency and service quality of a college management platform are not influenced.

Description

Technical Field

[0001] The present invention relates to the technical field of university platforms, and more specifically, to a relationship inference method oriented to a person relationship network. Background Art

[0002] The relationship inference method for character relationship networks refers to a method of analyzing and inferring relationships between characters, which is usually used in social network analysis, social network analysis, crime investigation, knowledge graph construction and other fields; in the technical field of university management platform, the relationship inference method for character relationship networks can help universities more effectively manage the relationships between students, faculty and other relevant personnel, optimize resource allocation, and improve management efficiency. It basically includes data collection, construction of character relationship networks, feature extraction, relationship inference and application, result analysis and visualization, continuous updating and optimization. By applying the relationship inference method for character relationship networks to the university management platform, more intelligent and personalized management and services can be achieved, which can improve the teaching, scientific research and management efficiency of universities, and promote communication and cooperation between students, faculty and alumni.

[0003] The prior art has the following deficiencies:

[0004] However, when the existing relationship inference method for person relationship network is running on the university management platform, it often performs relationship inference on the students, faculty and other relevant personnel of the university on the basis of assuming that there is no problem with the system in which the relationship inference method for person relationship network is located. Once the operating status of the system in which the relationship inference method for person relationship network is located has a problem and is not discovered in time, the relationship inference of the students, faculty and other relevant personnel of the university is still performed through the system, which may cause inaccurate or invalid relationship inference results, thereby affecting the efficiency and service quality of the university management platform.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a relationship inference method for a person relationship network to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A relationship inference method for a person relationship network, the method is applied to an alarm system, wherein:

[0009] Obtaining inference operation data of a system corresponding to relationship inference for a person relationship network, and obtaining an inference error coefficient according to the inference operation data; the inference operation data includes at least one of an inference calculation time deviation coefficient, an inference scheduling data quantity coefficient, and a feedback response delay coefficient;

[0010] The inference error coefficient is compared with a preset threshold value, and an error signal is obtained according to the comparison result; the error signal is the inference error coefficient corresponding to when the inference error coefficient is not less than the preset threshold value;

[0011] A data set is established for the inferred error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system sends out an alarm.

[0012] In a preferred embodiment, the method for obtaining the inferred calculation time deviation coefficient is:

[0013] Obtain the time taken by the system corresponding to the relationship inference for the person relationship network to infer the results at different times within a fixed time, and process the time taken by the system to infer the results at different times to obtain a time series;

[0014] Take the average of the first few values ​​of the time series to get the initial EMA value, and denote the initial EMA value as EMA0;

[0015] Calculate the smoothing coefficient: The smoothing coefficient σ is a weight parameter, which usually takes a value between [0,1]. The calculation expression is: In the formula, A represents the time window size used by EMA;

[0016] Update EMA value: Use the recursive formula of EMA to update the EMA value. The calculated expression is: EMA t =σ*WE+(1-σ)*EMA t-1 ,EMA t represents the EMA value at the t-th time point, WE represents the actual calculation time at the t-th time point; EMA t-1 Represents the EMA value at the t-1th time point;

[0017] Calculate the inference calculation time deviation coefficient, the calculation expression is:

[0018]

[0019] Where WD is the inferred calculation time deviation coefficient.

[0020] In a preferred embodiment, the method for obtaining the inferred scheduling data quantity coefficient is:

[0021] The actual number of dispatch data and the preset number of dispatch data used by the system for obtaining the relationship inference of the person-to-person relationship network at different times within a fixed time are denoted as P and P respectively. 实 y and P 预 y , y represents the number of the actual number of scheduling data and the preset number of scheduling data used to derive the results at different times within a fixed time, y=1, 2, 3, 4, ..., m, m represents the number of numbers and is a positive integer;

[0022] Calculate the coefficient of the number of inferred scheduling data, and the calculation expression is:

[0023] Where PE is the coefficient of the number of inferred scheduling data.

[0024] In a preferred embodiment, the method for obtaining the feedback response delay coefficient is:

[0025] The logic for obtaining the feedback response delay coefficient is:

[0026] Partitioning time series data:

[0027] Record the response time data of the feedback mechanism as time series data, and divide the time series data into continuous windows according to a fixed time window size;

[0028] Calculate the feedback delay time in each time window:

[0029] In each time window, record the time t of user feedback feedback and the corresponding recommended time t recommendation , and then calculate the feedback delay time. The delay time δt can be defined as the difference between the feedback time and the recommended time, δt = t feedback -t recommendation ;

[0030] Calculate the feedback response delay coefficient:

[0031] For each time window, the feedback delay coefficient in the time window can be calculated according to the calculated delay time. The feedback response delay coefficient FG can be calculated by the following formula:

[0032]

[0033] Wherein, n represents the number of feedback data points in the time window, and i represents the delay time of the i-th feedback data point.

[0034] In a preferred embodiment, obtaining the inference error coefficient according to the inferred operation data includes:

[0035] The inferred calculation time deviation coefficient, the inferred scheduling data quantity coefficient and the feedback response delay coefficient are used to construct a model, and the model calculation expression is:

[0036]

[0037] In the formula, Wgh is the inference error coefficient, WD, PE and PG represent the inference calculation time deviation coefficient, the inference scheduling data quantity coefficient and the feedback response delay coefficient respectively, α, β, γ are the proportional coefficients of the system load growth amplitude, the alarm response delay ratio and the signal disconnection change coefficient, and α, β, γ are all greater than 0.

[0038] In a preferred embodiment, a data set is established for the inference error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system issues an alarm, including:

[0039] If the standard deviation is less than a preset threshold, a low risk signal is generated, and the alarm system does not sound an alarm;

[0040] If the standard deviation is not less than a preset threshold, a risk signal is generated and the alarm system sounds an alarm.

[0041] Technical effects and advantages of the present invention:

[0042] The present invention obtains the inference operation data of the system corresponding to the relationship inference for the character relationship network, obtains the inference error coefficient according to the inference operation data, and compares the inference error coefficient with a preset threshold value. When the inference error coefficient is less than the preset threshold value, it is recorded as an error signal, and a data set is established for the inference error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with the preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system sends an alarm. In this way, the operation of the relationship inference method for the character relationship network on the university management platform is judged. When there is a problem in the system where the relationship inference method for the character relationship network is located, an alarm is promptly sent to remind the staff that there is a problem in the system where the relationship inference method for the character relationship network is located and timely maintenance is required to ensure that the relationship inference results of students, faculty and staff and other relevant personnel of the university are accurate or invalid, and do not affect the efficiency and service quality of the university management platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0044] Figure 1 A method flow chart of a relationship inference method for a person relationship network provided by the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example

[0047] Embodiment 1 of the present invention provides a relationship inference method for a person relationship network. Figure 1 , Figure 1 A flowchart of a relationship inference method for a person relationship network provided by an embodiment of the present invention, the method is applied to an alarm system, wherein:

[0048] Obtaining inference operation data of a system corresponding to relationship inference for a person relationship network, and obtaining an inference error coefficient according to the inference operation data; the inference operation data includes at least one of an inference calculation time deviation coefficient, an inference scheduling data quantity coefficient, and a feedback response delay coefficient;

[0049] The inference error coefficient is compared with a preset threshold value, and an error signal is obtained according to the comparison result; the error signal is the inference error coefficient corresponding to when the inference error coefficient is not less than the preset threshold value;

[0050] The inferred error coefficient corresponding to the error signal is used to establish a data set, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold. When the standard deviation is not less than the preset threshold, the alarm system sounds an alarm.

[0051] In one implementation, by obtaining the inference operation data of the system corresponding to the relationship inference for the character relationship network, the inference error coefficient is obtained according to the inference operation data, and the inference error coefficient is compared with a preset threshold value. When the inference error coefficient is less than the preset threshold value, it is recorded as an error signal, and a data set is established for the inference error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with the preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system sends an alarm. In this way, the operation of the relationship inference method for the character relationship network on the university management platform is judged. When there is a problem in the system where the relationship inference method for the character relationship network is located, an alarm is promptly sent to remind the staff that there is a problem in the system where the relationship inference method for the character relationship network is located and timely maintenance is required to ensure that the relationship inference results of the students, faculty and staff and other relevant personnel of the university are accurate or invalid, and do not affect the efficiency and service quality of the university management platform.

[0052] In one embodiment, the method for obtaining the inferred calculation time deviation coefficient is:

[0053] Obtain the time taken by the system corresponding to the relationship inference for the person relationship network to infer the results at different times within a fixed time, and process the time taken by the system to infer the results at different times to obtain a time series;

[0054] Take the average of the first few values ​​of the time series to get the initial EMA value, and denote the initial EMA value as EMA0;

[0055] Calculate the smoothing coefficient: The smoothing coefficient σ is a weight parameter, which usually takes a value between [0,1]. The calculation expression is: In the formula, A represents the time window size used by EMA;

[0056] Update EMA value: Use the recursive formula of EMA to update the EMA value. The calculated expression is: EMA t =σ*WE+(1-σ)*EMA t-1 ,EMA t represents the EMA value at the t-th time point, WE represents the actual calculation time at the t-th time point; EMA t-1 Represents the EMA value at the t-1th time point;

[0057] Calculate the inference calculation time deviation coefficient, the calculation expression is:

[0058]

[0059] Where WD is the inferred calculation time deviation coefficient.

[0060] In one implementation, it should be noted that the inference calculation time deviation coefficient refers to the degree of deviation in the time when the system corresponding to the relationship inference for the person relationship network infers the relationship between students, faculty and other relevant personnel within a fixed time; if the degree of deviation is higher, it means that the operating state of the system itself in which the relationship inference method for the person relationship network is located is more likely to have problems. Through the system, the relationship inference of the students, faculty and other relevant personnel of the university may cause inaccurate or invalid relationship inference results, thereby affecting the efficiency and service quality of the university management platform. The reasons are:

[0061] System resource limitations: A high time deviation coefficient may mean that system resources (such as CPU, memory, storage, etc.) are limited and cannot effectively support the computing requirements of relationship inference. Limited system resources will lead to slower computing speed, thereby increasing the computing time of inference and reducing the real-time and accuracy of inference.

[0062] System overload: A high time deviation coefficient may indicate that the system is overloaded and exceeds its normal processing capacity. System overload will cause slower system response and longer processing time, thus affecting the efficiency and accuracy of relationship inference.

[0063] System stability issues: Fluctuations in the time deviation coefficient may indicate problems with system stability, such as unstable system operation and prone to errors. System stability issues can lead to unstable results in relationship inference, which may result in calculation errors or inference failures.

[0064] Algorithm efficiency issue: A high time deviation coefficient may be due to the fact that the algorithm used is inefficient or unsuitable for the current system environment. Inefficient algorithms will increase the computational burden of inference, resulting in increased time deviation, affecting the accuracy and real-time performance of inference.

[0065] Data processing delay: Data processing delay may lead to untimely updating of relationship data, affecting the real-time nature of relationship inference. Data processing delay may cause the inference results to be based on outdated or incomplete data, reducing the accuracy of inference.

[0066] In summary, a high time deviation coefficient may indicate problems with the system's own operating status, including system resource limitations, system overload, system stability issues, algorithm efficiency issues, and data processing delays. These problems may reduce the computational efficiency of the relationship inference method for the person relationship network, and affect the accuracy and real-time performance of the inference results. Therefore, by observing the level of the time deviation coefficient, we can indirectly understand the system's operating status and the performance of the relationship inference method.

[0067] In one embodiment, the method for obtaining the inferred scheduling data quantity coefficient is:

[0068] The actual number of dispatch data and the preset number of dispatch data used by the system for obtaining the relationship inference of the person-to-person relationship network at different times within a fixed time are denoted as P and P respectively. 实 y and P 预 y , y represents the number of the actual number of scheduling data and the preset number of scheduling data used to derive the results at different times within a fixed time, y=1, 2, 3, 4, ..., m, m represents the number of numbers and is a positive integer;

[0069] Calculate the coefficient of the number of inferred scheduling data, and the calculation expression is:

[0070] Where PE is the coefficient of the number of inferred scheduling data.

[0071] In one implementation, the coefficient of the number of inferred scheduling data refers to the difference between the actual number of scheduling data used by the system corresponding to the relationship inference for the person relationship network to infer the results at different times within a fixed time and the preset number of scheduling data; if the difference is larger, it means that the system itself in which the relationship inference method for the person relationship network is located is more likely to have problems in its operating state. The relationship inference of students, faculty and other relevant personnel of the university through the system may lead to inaccurate or invalid relationship inference results, thereby affecting the efficiency and service quality of the university management platform. The reasons are:

[0072] System efficiency issues: A high inference scheduling data quantity coefficient means that the amount of data processed in the same time period far exceeds expectations, which may lead to reduced system efficiency. Reduced system efficiency will increase the time required to process each data point, thereby increasing the difference between the actual amount of data processed and the preset value.

[0073] Data quality issues: A high coefficient for the number of inference scheduling data may be due to data quality issues, such as duplicate, erroneous, or incomplete data. Data quality issues can make data processing more complex and time-consuming, thus affecting the number of inference scheduling data.

[0074] Therefore, when the coefficient of the number of inferred scheduling data is high, it may mean that there is a high possibility that there is a problem with the system operation status. This is because processing a large amount of data requires the system to have sufficient resources and efficiency, and also requires system stability and high-quality data support. A high coefficient of the number of inferred scheduling data reflects the challenges and limitations encountered by the system when processing data, which may affect the accuracy and real-time performance of relationship inference. Therefore, this coefficient can be used as an important indicator to evaluate the system operation status and the performance of the relationship inference method.

[0075] In one embodiment, the method for obtaining the feedback response delay coefficient is:

[0076] The logic for obtaining the feedback response delay coefficient is:

[0077] Partitioning time series data:

[0078] Record the response time data of the feedback mechanism as time series data, and divide the time series data into continuous windows according to a fixed time window size;

[0079] Calculate the feedback delay time in each time window:

[0080] In each time window, record the time t of user feedback feedback and the corresponding recommended time t recommendation , and then calculate the feedback delay time. The delay time δt can be defined as the difference between the feedback time and the recommended time, δt = t feedback -t recommendation ;

[0081] Calculate the feedback response delay coefficient:

[0082] For each time window, the feedback delay coefficient in the time window can be calculated according to the calculated delay time. The feedback response delay coefficient FG can be calculated by the following formula:

[0083]

[0084] Wherein, n represents the number of feedback data points in the time window, and i represents the delay time of the i-th feedback data point.

[0085] In one implementation, the feedback response delay coefficient refers to the delay degree of the relationship inference results of the students, faculty and other relevant personnel of the university output by the system corresponding to the relationship inference for the person relationship network within a fixed time. The higher the delay degree, the greater the possibility that there is a problem with the operating state of the system itself in which the relationship inference method for the person relationship network is located. The relationship inference results of the students, faculty and other relevant personnel of the university may be inaccurate or invalid through the system, thereby affecting the efficiency and service quality of the university management platform. The reasons are:

[0086] Real-time performance: A high latency factor means that the system has a delay in outputting results. A high latency factor may indicate that the system cannot respond to users or process tasks in a timely manner, which affects the real-time and instant performance of the system.

[0087] System health: A persistently high latency factor may reflect poor overall system health. Stable system operation is key, and persistent latency increases may indicate system failures, errors, or other health issues.

[0088] Therefore, a high feedback response delay coefficient usually indicates that there may be some operating problems in the system.

[0089] In one embodiment, obtaining the inference error coefficient according to the inference operation data includes:

[0090] The inference calculation time deviation coefficient, the inference scheduling data quantity coefficient and the feedback response delay coefficient are used to construct a model. The model calculation expression is:

[0091]

[0092] Where Wgh is the inference error coefficient, WD, PE and FG represent the inference calculation time deviation coefficient, the inference scheduling data quantity coefficient and the feedback response delay coefficient respectively, α, β and γ are the proportional coefficients of the system load growth amplitude, the alarm response delay ratio and the signal disconnection change coefficient, and α, β and γ are all greater than 0.

[0093] In one implementation,

[0094] In one embodiment, a data set is established for the inference error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system issues an alarm, including:

[0095] If the standard deviation is less than the preset threshold, a low risk signal is generated and the alarm system does not sound an alarm;

[0096] If the standard deviation is not less than the preset threshold, a risk signal is generated and the alarm system sounds an alarm.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0098] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0099] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0100] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0101] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A relationship inference method for a person relationship network, characterized in that: The method is applied to an alarm system, wherein: Obtaining inference operation data of a system corresponding to relationship inference for a person relationship network, and obtaining an inference error coefficient according to the inference operation data; the inference operation data includes at least one of an inference calculation time deviation coefficient, an inference scheduling data quantity coefficient, and a feedback response delay coefficient; The inference error coefficient is compared with a preset threshold value, and an error signal is obtained according to the comparison result; the error signal is the inference error coefficient corresponding to when the inference error coefficient is not less than the preset threshold value; A data set is established for the inferred error coefficient corresponding to the error signal, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system sends out an alarm.

2. A method for inferring relationships among people's relationships according to claim 1, characterized in that: The method for obtaining the inferred calculation time deviation coefficient is: Obtain the time taken by the system corresponding to the relationship inference for the person relationship network to infer the results at different times within a fixed time, and process the time taken by the system to infer the results at different times to obtain a time series; Take the average of the first few values ​​of the time series to get the initial EMA value, and denote the initial EMA value as EMA0; Calculate the smoothing coefficient: The smoothing coefficient σ is a weight parameter, which usually takes a value between [0,1]. The calculation expression is: In the formula, A represents the time window size used by EMA; Update EMA value: Use the recursive formula of EMA to update the EMA value. The calculated expression is: EMA t =σ*WE+(1-σ)*EMA t-1 ,EMA t represents the EMA value at the t-th time point, WE represents the actual calculation time at the t-th time point; EMA t-1 Represents the EMA value at the t-1th time point; Calculate the inference calculation time deviation coefficient, the calculation expression is: Where WD is the inferred calculation time deviation coefficient.

3. The method for inferring a relationship based on a person relationship network according to claim 1, characterized in that: The method for obtaining the inferred scheduling data quantity coefficient is: The actual number of dispatch data and the preset number of dispatch data used by the system for obtaining the inference results of the relationship inference of the person-to-person relationship network at different times within a fixed time are denoted as P and P respectively. 实 y and P 预 y , y represents the number of the actual number of scheduling data and the preset number of scheduling data used to derive the results at different times within a fixed time, y=1, 2, 3, 4, ..., m, m represents the number of numbers and is a positive integer; Calculate the coefficient of the number of inferred scheduling data, and the calculation expression is: Where PE is the coefficient of the number of inferred scheduling data.

4. The method for inferring a relationship based on a person relationship network according to claim 1, characterized in that: The method for obtaining the feedback response delay coefficient is: The logic for obtaining the feedback response delay coefficient is: Partitioning time series data: Record the response time data of the feedback mechanism as time series data, and divide the time series data into continuous windows according to a fixed time window size; Calculate the feedback delay time in each time window: In each time window, record the time t of user feedback feedback and the corresponding recommended time t recommendation , and then calculate the feedback delay time. The delay time δt can be defined as the difference between the feedback time and the recommended time, δt = t feedback -t recommendation ; Calculate the feedback response delay coefficient: For each time window, the feedback delay coefficient in the time window can be calculated according to the calculated delay time. The feedback response delay coefficient FG can be calculated by the following formula: Wherein, n represents the number of feedback data points in the time window, and i represents the delay time of the i-th feedback data point.

5. The method for inferring a relationship based on a person relationship network according to claim 1, characterized in that: The inference error coefficient obtained according to the inference operation data includes: The inferred calculation time deviation coefficient, the inferred scheduling data quantity coefficient and the feedback response delay coefficient are used to construct a model, and the model calculation expression is: In the formula, Wgh is the inference error coefficient, WD, PE and FG respectively represent the inference calculation time deviation coefficient, the inference scheduling data quantity coefficient and the feedback response delay coefficient, α, β, γ are the proportional coefficients of the system load growth amplitude, the alarm response delay ratio and the signal disconnection change coefficient, and α, β, γ are all greater than 0.

6. The method for inferring a relationship based on a person relationship network according to claim 1, characterized in that: The inference error coefficient corresponding to the error signal is used to establish a data set, and the standard deviation of the data set is calculated, and the standard deviation is compared with a preset threshold value. When the standard deviation is not less than the preset threshold value, the alarm system issues an alarm, including: If the standard deviation is less than a preset threshold, a low risk signal is generated, and the alarm system does not sound an alarm; If the standard deviation is not less than a preset threshold, a risk signal is generated and the alarm system sounds an alarm.

Images