Information processing method and device, evaluation parameter output device and system and medium

Abstract

The embodiment of the invention provides an information processing method and device, an evaluation parameter output device and system and a medium, belongs to the technical field of information processing, and aims to improve the automation level of region management and control, the method comprises the steps of obtaining multiple pieces of service information of an entity region in a target service, the multiple pieces of service information at least comprise information used for describing states of different facilities in the entity area; according to a plurality of preset dimensions, clustering the plurality of pieces of service information to obtain dimension information corresponding to the plurality of preset dimensions; obtaining evaluation parameters respectively corresponding to the plurality of preset dimensions; determining a grading parameter of the entity area on the target business based on the plurality of evaluation parameters and the plurality of dimension information; wherein the grading parameter is used for indicating the grade to which the entity area belongs.

Description

Information processing method and device, evaluation parameter output device, system and medium Technical Field

[0001] The present disclosure relates to the field of information processing technology, and in particular to an information processing method and device, an evaluation parameter output device, a system, and a medium. Background Art

[0002] In some scenarios, comprehensive management and control of physical areas is required. Generally, the physical area's performance in certain services is regularly assessed, and management and control of the physical area is implemented based on the assessment results. This physical area can be a building or a geographic area, and services subject to level assessments include fire safety assessments, medical safety assessments, and pedestrian flow assessments.

[0003] For example, for building areas, it is necessary to continuously evaluate the fire safety performance of the building during the use of the building; if the building is a hospital, it is also necessary to evaluate the hospital's health defense performance; if the physical area is a scenic area, it is necessary to evaluate the scenic area's safety protection performance for pedestrians based on the flow of people in the scenic area.

[0004] Overview

[0005] In a first aspect, the present disclosure provides an information processing method, the method comprising:

[0006] Acquire a plurality of business information of the physical area in the target business, wherein the plurality of business information at least includes information for describing the status of different facilities in the physical area;

[0007] Clustering the plurality of business information according to a plurality of preset dimensions to obtain dimension information corresponding to each of the plurality of preset dimensions;

[0008] Obtaining evaluation parameters corresponding to each of the plurality of preset dimensions;

[0009] Based on the multiple evaluation parameters and the multiple dimension information, a grading parameter of the entity area for the target business is determined; wherein the grading parameter is used to indicate the level to which the entity area belongs.

[0010] In some optional examples, obtaining evaluation parameters corresponding to each of the plurality of preset dimensions includes:

[0011] Obtaining evaluation factors corresponding to respective preset dimensions, and establishing association relationships between the multiple evaluation factors; wherein the association relationships include direct association relationships and indirect association relationships;

[0012] Based on the association relationship, determining the initial weight of each evaluation factor;

[0013] Based on the initial weights, evaluation parameters corresponding to the preset dimensions are determined.

[0014] In some optional examples, the constructing of association relationships among the multiple evaluation factors includes:

[0015] receiving an inputted influence relationship for a plurality of the evaluation factors, wherein the influence relationship is used to represent that the evaluation factors have a direct correlation;

[0016] Based on the influence relationship, the association relationship is constructed.

[0017] In some optional examples, determining the evaluation parameters corresponding to each of the preset dimensions based on the initial weights includes:

[0018] Determining an influence parameter of a first evaluation factor on a second evaluation factor having an associated relationship, wherein the influence parameter is used to characterize the degree of influence of the first evaluation factor on the second evaluation factor; wherein the first evaluation factor is any evaluation factor among the plurality of evaluation factors;

[0019] Adjusting the initial weight of the second evaluation factor based on the influencing parameter;

[0020] Based on the adjusted initial weights, the evaluation parameters corresponding to the respective preset dimensions are determined.

[0021] In some optional examples, determining the evaluation parameters corresponding to each of the preset dimensions based on the initial weights includes:

[0022] Sequentially adjusting the initial weights of the plurality of evaluation factors, wherein each time an evaluation factor is adjusted, the initial weights of the evaluation factors associated with the evaluation factor are adjusted based on a random number corresponding to the evaluation factor;

[0023] Repeating the step of sequentially adjusting the initial weights of the multiple evaluation factors for multiple rounds to obtain the adjusted initial weights of the multiple evaluation factors corresponding to the multiple rounds of adjustments;

[0024] Based on the adjusted initial weights of the multiple evaluation factors respectively corresponding to the multiple rounds of adjustments, the evaluation parameters respectively corresponding to the multiple preset dimensions are obtained.

[0025] In some optional examples, adjusting the initial weight of the evaluation factor associated with the evaluation factor based on the random number corresponding to the evaluation factor includes:

[0026] When the initial weight of the evaluation factor is greater than the random number, adjusting the initial weight of the evaluation factor associated with the evaluation factor;

[0027] In the case that the initial weight of the evaluation factor is not greater than the random number, the initial weight of the evaluation factor associated with the evaluation factor after the last adjustment is retained.

[0028] In some optional examples, adjusting the initial weight of the evaluation factor associated with the evaluation factor based on the random number corresponding to the evaluation factor includes:

[0029] Determining an influence parameter of the evaluation factor on an evaluation factor having an associated relationship, wherein the influence parameter may represent the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor;

[0030] Based on the influencing parameter, the initial weight of the evaluation factor associated with the evaluation factor is adjusted.

[0031] In some optional examples, obtaining evaluation parameters corresponding to each of the plurality of preset dimensions based on the adjusted initial weights of the plurality of evaluation factors respectively corresponding to the plurality of evaluation factors in the plurality of rounds of adjustments includes:

[0032] Constructing a cross-influence probability matrix based on the influencing parameters between the evaluation factors having the correlation relationship;

[0033] Performing multiple iterative preset operations on the cross-influence probability matrix and the adjusted initial weights corresponding to the multiple evaluation factors in multiple rounds of adjustments until a preset end condition is reached;

[0034] Based on the cross-influence probability matrix when the preset end condition is reached, evaluation parameters corresponding to each of the plurality of preset dimensions are obtained.

[0035] In some optional examples, determining the grading parameter of the entity area for the target business based on the multiple evaluation parameters and the multiple dimensional information includes:

[0036] quantizing the plurality of dimensional information to obtain a quantized value corresponding to each dimensional information;

[0037] Determining quantitative scoring values ​​corresponding to the plurality of evaluation factors based on the plurality of evaluation parameters and the plurality of quantitative values;

[0038] The ranking parameters are determined based on the respective quantitative score values.

[0039] In some optional examples, after determining the quantitative score values ​​corresponding to the plurality of evaluation factors based on the plurality of evaluation parameters and the plurality of quantitative values, the method further includes:

[0040] determining a difference between the evaluation parameter and the corresponding quantitative score value;

[0041] determining at least one target evaluation factor from the plurality of evaluation factors based on the difference;

[0042] Output recommendation information corresponding to each of the target evaluation factors.

[0043] In some optional examples, the plurality of business information comes from a plurality of information collection devices, and the method further includes:

[0044] In the case where the grading parameter is lower than the preset grading parameter, determining a target preset dimension where the difference between the quantitative rating value and the evaluation parameter is greater than a preset difference;

[0045] Control the target information collection device to output warning information; wherein, the target information collection device is used to collect business information of the target preset dimension.

[0046] In some optional examples, the method further includes:

[0047] Obtaining classification parameters corresponding to the physical area in a plurality of different time periods;

[0048] Based on the corresponding grading parameters in the multiple different time periods, the grading statistical information of the physical area is output to indicate the grading changes of the physical area in the target business in the different time periods.

[0049] In some optional examples, obtaining multiple business information of the entity area in the target business includes:

[0050] When a preset time period arrives, in response to a classification target of the preset time period, obtaining business information of the physical area corresponding to the classification target in the target business; wherein the classification targets corresponding to different preset time periods are the same or different;

[0051] Among them, the multiple preset dimensions correspond to the classification targets.

[0052] In some optional examples, obtaining multiple business information of the entity area in the target business includes:

[0053] Sending an information collection instruction to a plurality of information collection devices located in the physical area to instruct the information collection devices to collect the facility status of the configured facilities;

[0054] Acquire the business information collected by the multiple information collection devices after performing the information collection.

[0055] A second aspect of the present disclosure provides an information processing system, comprising an Internet of Things platform and a plurality of information collection devices connected to the Internet of Things platform; wherein:

[0056] The multiple information collection devices are used to collect business information of the entity area on the target business;

[0057] The Internet of Things platform is used to execute the information processing method.

[0058] According to a third aspect of the present disclosure, there is provided an evaluation parameter output device, the device comprising:

[0059] A factor acquisition module is used to acquire multiple evaluation factors corresponding to a target business in a physical area; wherein one evaluation factor corresponds to a preset dimension of the target business;

[0060] A parameter determination module is used to determine the evaluation parameters corresponding to the various evaluation factors;

[0061] an output module, configured to send the evaluation parameters to an information processing platform, so that the information processing platform determines a grading parameter of the entity area for the target business based on a plurality of the evaluation parameters and a plurality of dimensional information; wherein the grading parameter is used to indicate the grade to which the entity area belongs;

[0062] The dimension information is obtained by clustering multiple businesses according to multiple preset dimensions, and the multiple business information at least includes status information of different facilities in the physical area.

[0063] In some optional examples, the parameter determination module includes:

[0064] A relationship building unit, used to build a correlation relationship between the multiple evaluation factors;

[0065] A weight acquisition unit, configured to output the association relationship and receive an initial weight input for each evaluation factor;

[0066] A parameter determination unit is used to determine the evaluation parameters corresponding to each of the preset dimensions based on the initial weights.

[0067] In some optional examples, the apparatus further includes: an influencing parameter determination module and an adjustment module;

[0068] The impact parameter determination module is configured to receive impact parameters inputted for associated evaluation factors, wherein the impact parameters are used to represent the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor;

[0069] The adjustment module is configured to adjust the initial weight of each of the evaluation factors based on the influencing parameters;

[0070] The parameter determination unit is specifically configured to determine the evaluation parameters corresponding to each of the preset dimensions based on the adjusted initial weights.

[0071] In some optional examples, the apparatus further includes: an iterative adjustment module;

[0072] The iterative adjustment module is used to sequentially adjust the initial weights of the plurality of evaluation factors, wherein, when each evaluation factor is adjusted, the initial weights of the evaluation factors associated with the evaluation factor are adjusted based on the random number corresponding to the evaluation factor;

[0073] wherein, when adjusting the initial weight of the evaluation factor associated with the evaluation factor, the initial weight of the evaluation factor is adjusted using the influencing parameter determination module and the adjustment module;

[0074] The parameter determination unit is specifically configured to obtain evaluation parameters corresponding to each of the plurality of preset dimensions based on the adjusted initial weights of the plurality of evaluation factors respectively corresponding to the plurality of evaluation factors in multiple rounds of adjustment.

[0075] In some optional examples, the factor acquisition module is used to acquire the multiple evaluation factors from a database corresponding to the target business.

[0076] In some optional examples, the information processing platform is an Internet of Things platform, or the information processing platform and the output device are integrated into the Internet of Things platform.

[0077] An embodiment of the present disclosure also discloses an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the information processing method as described in the embodiment of the first aspect.

[0078] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is further disclosed, wherein the computer program stored in the medium enables a processor to execute the information processing method as described in the embodiment of the first aspect of the present disclosure.

[0079] The information processing method proposed in the embodiment of the present disclosure can obtain multiple business information of the physical area in the target business, and cluster the multiple business information according to multiple preset dimensions to obtain dimensional information corresponding to each of the multiple preset dimensions; then, obtain evaluation parameters corresponding to each of the multiple preset dimensions, and then determine the grading parameters of the physical area in the target business based on the multiple evaluation parameters and the multiple dimensional information; wherein the multiple business information at least includes information for describing the status of different facilities in the physical area.

[0080] Since the acquired business information includes at least information for describing the status of the facilities in the physical area, the information on the status of the facilities can be used to characterize whether the facilities are aging, whether there are any faults, etc., thereby reflecting the maintenance status of the physical area in the current period of time; after clustering the business information according to the preset dimensions, the business information reflecting the same dimension can be summarized and counted, and then, based on the summarized and counted dimensional information and the evaluation parameters corresponding to each preset dimension, the level of the physical area in the target business can be evaluated, so that the level of the physical area can be determined based on the dimensional information of the physical area with the evaluation parameters corresponding to the preset dimensions as the benchmark. In this way, the automated evaluation of the level of the physical area in the target business is achieved, while minimizing manual participation, providing a highly applicable implementation solution for the automated management and control of buildings.

[0081] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below.

[0082] BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for the description of the embodiments or related technologies. Obviously, the drawings described below are some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. It should be noted that the scales in the drawings are for illustration only and do not represent the actual scale.

[0084] FIG1 shows an implementation environment diagram of an information processing method in an embodiment of the present disclosure;

[0085] FIG2 shows a flowchart of the steps of the information processing method in an embodiment of the present disclosure;

[0086] FIG3 shows a schematic diagram of the correlation between the constructed evaluation factors, taking Table 1 as an example;

[0087] FIG4 a shows a schematic flow chart of the steps for adjusting the initial weights;

[0088] FIG4 b takes fire safety as an example and shows a schematic diagram of setting the influencing parameters of 23 evaluation factors;

[0089] FIG5 is a schematic diagram showing a process of performing multiple rounds of adjustments to the initial weights;

[0090] FIG6 shows a schematic flow chart of steps for solving evaluation parameters in the case of multiple rounds of adjustments;

[0091] FIG7 shows a schematic diagram of the framework structure of an evaluation parameter output device;

[0092] FIG8 shows a schematic diagram of a framework structure of an information processing system.

[0093] Detailed description

[0094] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0095] In related technologies, when comprehensive management and control of physical areas is generally carried out, it is necessary to evaluate the level of the physical area in the target business and to control the physical area based on the evaluation results. However, current evaluation strategies are generally based on human evaluation, and most of the management and control also rely on human management, which consumes more human resources and has high human resource expenditure costs.

[0096] In view of this, the present disclosure proposes a solution that can automatically evaluate the level of the entity area in the target business, so as to carry out automated integrated management and control of the entity area. The core concept is to collect a variety of business information of the entity area in the target business, and then cluster the various business information into a variety of dimensional information according to a variety of preset dimensions. After that, the various dimensional information is evaluated according to the evaluation parameters corresponding to each of the multiple preset dimensions, so as to obtain the grading parameters of the entity area in the target business. Among them, the evaluation parameter can be used to indicate the evaluation benchmark of the entity area under the preset dimension of the target business. The preset dimension can be set in advance, and the business information can be automatically collected. Then, when the entity area is evaluated based on the dimensional information according to the evaluation parameter, the level of the dimensional information can be determined according to the benchmark indicated by the evaluation parameter. Then, the grading parameters of the entity area in the target business are determined by combining the levels of the various dimensional information, thereby achieving the purpose of automated evaluation and automated management and control, minimizing manual participation in evaluation and management, and reducing labor cost expenditure.

[0097] Application scenarios of this application may include: fire safety assessments of buildings, medical disinfection assessments of medical facilities such as hospitals, and pedestrian flow safety assessments of scenic spots. Of course, the above application scenarios do not limit this disclosure; in practice, it can also be applied to other scenarios.

[0098] Referring to Figure 1, an implementation environment diagram of an information processing method of the present application is shown. Figure 1 takes the fire safety assessment of a building as an example, which may include an information processing platform and a variety of information collection devices arranged in the building 100. As shown in Figure 1, the various information collection devices include devices, tablets and computers. The information processing platform communicates with the various information collection devices. The communication connection can be TCP (Transmission Control Protocol), HTTP (Hyper Text Transfer Protocol), MQTT (Message Queuing Telemetry Transport) and other connections. The information collection equipment is used to collect status information of different facilities in the building. The information processing platform can be an Internet of Things platform, and the information processing platform can be located in the cloud or in a server within a local area network.

[0099] Among them, the various information collection devices may be different depending on the type of information to be collected. Specifically, each type of business information may correspond to an information collection device, which may be a sensor, computer, camera, tablet, mobile phone, etc.

[0100] The various information collection devices can be partially or entirely located within the physical area, or partially located within the physical area and partially located outside the physical area as mobile information collection devices. For example, if the information collection device is a sensor or camera, it is located within the physical area to collect information about the status of the facilities within the physical area. If the information collection device is a tablet, computer, mobile phone, etc., it can be located outside the physical area to collect information about the implementation status of measures to execute the target business.

[0101] Taking fire safety assessment as an example, if the business information to be collected includes the fire hydrant system, the information collection equipment may include a camera for collecting images of the fire hydrants and processing the images of the fire hydrants to obtain the status of the fire hydrants; if the business information to be collected is the fire water supply facilities, it is necessary to detect the integrity of the fire water supply facilities, and the information collection equipment may be a water pressure sensor for collecting the water pressure status of the fire water supply facilities.

[0102] Of course, in some other embodiments, the information collection device can be integrated into fire protection facilities, such as smoke alarms, which can detect the smoke alarms in real time to determine whether the smoke alarms are faulty and send business information based on the detection results.

[0103] Taking medical safety assessment as an example, if the business information to be collected includes the ventilation system, the information collection equipment may include an air flow sensor for collecting the air flow at various locations in the ventilation system; if the business information to be collected is the working status of each disinfection equipment in the disinfection room, the information collection equipment may be a sensor integrated into each disinfection equipment for collecting status information of the disinfection equipment.

[0104] In conjunction with the implementation environment shown in FIG1 , an information processing method of the present disclosure is described. FIG2 shows a flowchart of the steps of the information processing method. As shown in FIG2 , the method can be applied to an information processing platform, which can be located in the cloud or in a server. The method can specifically include the following steps:

[0105] Step S201: Acquire multiple business information of the entity area in the target business;

[0106] The plurality of business information includes at least information for describing the status of different facilities in the physical area.

[0107] The physical area in the present disclosure may refer to a building area, such as a shopping mall, a large summer building, etc., or may refer to a geographical area including open areas and buildings, such as a scenic spot; wherein, the target business may be understood as a business that needs to be evaluated in the physical area. For example, if the physical area needs to be evaluated on fire safety, the target business may refer to a fire safety evaluation business. If the physical area needs to be evaluated on health defense, the target business may refer to a medical safety evaluation business. If the physical area is a scenic spot, and it needs to evaluate the level of pedestrian safety protection under conditions of high pedestrian flow, the target business may refer to a pedestrian safety protection business.

[0108] Among them, one physical area can correspond to multiple target businesses, that is, the physical area can be evaluated on multiple target businesses.

[0109] The multiple business information may include information describing the status of various facilities within a physical area. The facility status may refer to the facility's operating status, and this business information may reflect whether the facilities within the physical area are experiencing any malfunctions or their performance. In some examples, the multiple business information may also include information about management measures implemented by the physical area to meet the target business assessment standards. This business information may be input by a user into an electronic device, such as a mobile phone, tablet, or computer. For example, in the case of a fire safety assessment, the user may input the corresponding business information about a fire drill conducted for fire safety into the electronic device.

[0110] It is understandable that multiple business information may include multiple business information of the same type. For example, for the ventilation facilities of a hospital, air flow sensors are generally installed at multiple locations, which will generate multiple air flow information. Different air flow information reflects the ventilation conditions at different locations.

[0111] Step S202: clustering the plurality of business information according to the plurality of preset dimensions to obtain dimension information corresponding to each of the plurality of preset dimensions.

[0112] In the present disclosure, multiple preset dimensions may refer to dimensions that affect the evaluation of an entity area in a target business. For example, taking fire safety assessment as an example, the dimensions that affect the fire safety assessment of a building may be 23 dimensions. As shown in Table 1 of the subsequent embodiments, multiple business information may be clustered according to multiple preset dimensions. During clustering, the business information reflecting the same preset uniqueness may be treated as a cluster, thereby obtaining multiple dimensional information.

[0113] Among them, multiple preset dimensions can be pre-stored in the information processing platform and correspond to target businesses. That is, each target business corresponds to its own multiple preset dimensions.

[0114] Among them, each dimension information of the multiple dimensional information obtained by clustering can include at least one business information. When the dimensional information includes multiple business information, the multiple business information can be the same type of information, such as the business information about ventilation status in the above example; of course, the multiple business information can also be different types of information. For example, in the fire safety assessment business, the preset dimension is building safe evacuation, then the multiple business information can include information such as stairs, passages, and walkways.

[0115] Step S203: Obtain evaluation parameters corresponding to each of the plurality of preset dimensions.

[0116] Among them, when obtaining the evaluation parameters corresponding to multiple preset dimensions, they can be obtained from the database. The evaluation parameters can be understood as the score value corresponding to the highest evaluation level of the entity area in the preset dimension. Taking the fire safety assessment business as an example, the preset dimension is building safety evacuation, and its evaluation parameter is 3, which means that reaching 3 points is considered to be the highest evaluation level. Therefore, the evaluation parameters can be regarded as the benchmark evaluation scores of the preset dimensions, so as to subsequently combine the dimensional information of the entity area to evaluate the entity area in the target business.

[0117] Step S204: Determine the grading parameters of the entity area for the target business based on the multiple evaluation parameters and multiple dimensional information;

[0118] The classification parameter is used to indicate the class to which the entity area belongs.

[0119] Since the business information is the actual information of the entity area on the target business, reflecting the actual situation of the facilities in the entity area and the measures to achieve the target business, and the evaluation parameters are the benchmark evaluation scores corresponding to the highest evaluation level of the entity area on the preset dimension, for each preset dimension, the score of the entity area on the preset dimension can be determined based on the evaluation parameters corresponding to the preset dimension and the dimensional information of the preset dimension. Then, based on the respective scores of the entity area on multiple preset dimensions, the comprehensive score of the entity area is obtained, and according to the comprehensive score, the grading parameters of the entity area on the target business can be determined.

[0120] Among them, the grading parameter can be a level parameter, such as whether the level is high, medium or low, or it can be a comprehensive score. If the full score system is a percentage system, the comprehensive score can be 80, 90, etc., then the grading parameter can be the score under the percentage system.

[0121] After obtaining the grading parameters, the grading parameters of the entity area can be displayed, or the grading parameters can be fed back to the terminal of the superior department of the entity area and the client corresponding to the entity area, so that the entity area can maintain and rectify the facilities of the entity area according to the scores of each preset dimension.

[0122] Using the disclosed embodiments, the acquired business information can be used to characterize whether a facility is aging or experiencing malfunctions, among other conditions. This information can be automatically collected by information collection equipment. After obtaining multiple pieces of business information, the business information can be clustered according to preset dimensions. Based on the clustered dimensional information and the evaluation parameters corresponding to each preset dimension, the grading parameters for the entity area's level in the target business are automatically determined. This achieves a highly automated process from information collection to grading parameter determination, reducing manual intervention and providing a highly applicable implementation solution for automated building management and control.

[0123] In some embodiments, when acquiring multiple business information of a physical area in a target business, the acquisition can be performed in different time periods to meet the requirement that the grading targets of the target business of the physical area can be different in different time periods. The grading target of the target business can refer to the degree of grade assessment of the target business. For example, in the case where the physical area is a scenic area, it can be divided into an off-season and a peak season. The assessment targets for pedestrian safety protection in the off-season and the peak season can be different, and therefore, the division of the preset dimensions can also be different. In this way, if the grading targets are different in different time periods, the types of preset dimensions can be different, and the types of business information acquired can be different.

[0124] In a specific implementation, when a preset period arrives, in response to the classification target of the preset period, business information corresponding to the classification target in the target business of the physical area can be obtained. The classification targets corresponding to different preset periods may be the same or different, and multiple preset dimensions may correspond to the classification targets.

[0125] Among them, in different time periods, when the classification targets are different, the types and quantities of business information obtained may also be different. Specifically, when the classification targets are different, the preset dimensions into which the same target business is divided may also be different in type and quantity. When the preset dimensions are different, the business information to be obtained will also be different.

[0126] For example, taking the physical area as a scenic spot, it can be divided into the off-season and the peak season. Among them, if the pedestrian safety protection is evaluated in the off-season, its grading target can be a more basic safety protection assessment, such as whether the safety fence is intact, whether the cable car parts are normal, whether the mountain has a landslide risk, etc., and the business information collected can be image collection of safety fences, cable car parts and roads; if the pedestrian safety protection is evaluated in the peak season, its grading target can be a higher protection requirement. In addition to the above-mentioned off-season protection requirements, it is also necessary to add: whether the safety rescue facilities (rescue vehicles) are sufficient, whether the crowd counting facilities are intact, etc.; secondly, if encountering the summer flood season, it is also necessary to increase the information collection of flood monitoring equipment in rivers, valleys, etc. to monitor whether these flood monitoring equipment are in normal working condition.

[0127] In the present disclosure, the preset time period can be stored in the information processing platform and can be preset in the timer. When the preset time period arrives, the information processing platform can send information collection instructions to the corresponding information collection device according to the classification target corresponding to the preset time period to collect the corresponding business information, thereby determining the subsequent classification parameters according to the multiple preset dimensions corresponding to the preset time period.

[0128] By adopting this implementation plan, the information processing platform can automatically match different grading target requirements according to different time periods, determine the grading parameters of the physical area that match the current time period, and achieve the logic and time period adaptation of information processing, thereby further improving the level of automation for automated management and control of physical areas.

[0129] Among them, when acquiring business information, as mentioned above, since the information processing platform can be connected to a variety of information collection devices, business information can be obtained by sending instructions to the information collection devices. In specific implementation, when the preset time period arrives, information collection instructions can be sent to multiple information collection devices located in the physical area to instruct the information collection devices to collect the facility status of the facilities they are configured to collect; then, the business information collected by multiple information collection devices after information collection is obtained.

[0130] As mentioned above, when the preset time period arrives, the information processing platform can determine the business information that needs to be collected based on the hierarchical target corresponding to the preset time period, and then send an information collection instruction to the information collection device that needs to collect business information. After receiving the information collection instruction, the information collection device starts collecting the corresponding business information.

[0131] When the information collection device is collecting information about facilities in a physical area, an information collection instruction can be sent to the information collection device via a communication link between the information processing platform and the information collection device. This information collection instruction can wake up and activate the information collection device, and after being woken up and activated, the information collection device can begin collecting the status of the facilities. In this way, the information collection device can sleep when business information collection is not needed to save energy. When business information collection is needed, it responds to the information collection instruction to wake up and begin collecting business information.

[0132] Among them, when the information collection device collects the protection measures taken for the target business in the physical area, the information collection instruction can be sent to the information collection device through the communication link between the information processing platform and the information collection device. The information collection device can display the information indicated by the information collection instruction to instruct the user to enter the relevant business information. After the user enters the information, the information entered by the user is reported to the information processing platform as business information.

[0133] When this implementation plan is adopted, whether it is business information corresponding to facilities or business information corresponding to measures, business information can be automatically collected, thereby reducing manual participation in information collection and saving labor cost expenditure.

[0134] Below, we will explain how to obtain the evaluation parameters corresponding to each of the multiple preset dimensions. To obtain more accurate evaluation parameters, you can first obtain the evaluation factors related to the multiple preset dimensions. The evaluation factors can be understood as information with the same meaning as the preset dimensions. For example, taking fire safety assessment as an example, the preset dimension is the dimension of building fire zoning, and the evaluation factor is the building fire zoning. Generally speaking, the hierarchical evaluation of an entity area in the target business is determined by its dimensional information in multiple preset dimensions. The dimensional information of a preset dimension is not isolated for evaluation, and it has mutual influence with the dimensional information of other preset dimensions. In other words, the dimensional information of multiple preset dimensions interacts with each other, and the result of the grade evaluation can be understood as the result of their interaction.

[0135] In practice, in some embodiments, in order to accurately determine the evaluation parameters of the evaluation factor, a correlation relationship between multiple evaluation factors can be first constructed to characterize the mutual influence of multiple evaluation factors on the grade evaluation, that is, to characterize the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor, so that according to the correlation relationship, the evaluation parameters of each evaluation factor can be accurately obtained.

[0136] In specific implementation, we can first obtain the evaluation factors corresponding to multiple preset dimensions, and build the correlation between the multiple evaluation factors; and based on the correlation, determine the initial weight of each evaluation factor; then, based on the initial weight, determine the evaluation parameters corresponding to each preset dimension.

[0137] In this embodiment, evaluation factors corresponding to multiple preset dimensions can be obtained from the database, with one evaluation factor corresponding to each preset dimension, or multiple evaluation factors corresponding to each preset dimension. Since the multiple evaluation factors are all factors related to the grading parameters of the entity area in evaluating the target business, an evaluation factor can represent an impact factor of the entity area on the target business, indicating that the event represented by the evaluation factor has an impact on the evaluation of the entity area in the target business. Taking fire safety assessment as an example, the evaluation factor is fire water supply facilities, which represents the impact of the fire water supply facilities in the entity area on fire safety.

[0138] Among them, taking fire safety assessment as an example, according to the impact of assessment factors on target business, assessment factors can be divided into direct factors, indirect factors and deep factors. Direct factors can be direct factors that lead to fire accidents, such as: fire zoning, facility integrity, fire hazards, etc.; indirect factors refer to reducing the potential possibility of fire from the source, such as: whether the secondary decoration meets the standards, the implementation of the fire safety responsibility system, fire safety system and operating procedures, fire drills, micro fire station management, etc.; deep factors are to reduce the source of fire through fire drills, such as: the legality of the building, whether fire extinguishing and emergency evacuation plans are prepared, and whether employees receive regular fire knowledge training.

[0139] As described above, for a target business, a single assessment factor has an impact on the physical area's assessment of the target business, and this impact is in turn influenced by other assessment factors. For example, the aforementioned indirect and deep factors may work together with direct factors to affect the physical area's fire safety. Therefore, multiple assessment factors influence each other. This disclosure can characterize the mutual influence between multiple assessment factors by constructing correlations between them.

[0140] Among them, the correlation relationship between evaluation factors can be constructed between evaluation factors that have mutual influence. For example, if evaluation factor A and evaluation factor B influence each other, a correlation relationship between evaluation factor A and evaluation factor B will be constructed; it can be understood that the correlation relationship can include direct correlation relationships and indirect correlation relationships.

[0141] Among them, a direct correlation refers to the direct influence between two evaluation factors. For example, taking fire safety assessment as an example, the building fire protection partition maintains compliance with fire protection standards as an evaluation factor A, and daily fire prevention and fire safety inspections are evaluation factor B. Then the evaluation factor A is directly affected by the evaluation factor B, and the two have a direct correlation.

[0142] Among them, an indirect correlation relationship refers to an indirect influence between two evaluation factors through another evaluation factor. For example, taking fire safety assessment as an example, the building fire protection partition maintains compliance with fire protection standards as an evaluation factor A, and daily fire prevention and fire safety inspections are evaluation factor B. Then evaluation factor A is directly affected by evaluation factor B. The functional properties of the building floor are in compliance with the original design as evaluation factor C, which is directly affected by evaluation factor B. Then evaluation factor A and evaluation factor C belong to an indirect influence relationship, that is, an indirect correlation relationship.

[0143] After obtaining the correlation between the evaluation factors, an internal logical topology diagram between multiple evaluation factors can be constructed. The internal logical topology diagram can reflect the influence relationship and influence degree between multiple evaluation factors. Therefore, based on the correlation relationship, the initial weight of each evaluation factor can be set. Generally speaking, for an evaluation factor, the more evaluation factors it has associated relationships with, the larger its initial weight can be, indicating that its evaluation of the level is more important.

[0144] The evaluation parameters can be understood as the weight values ​​obtained by adjusting the initial weights. The initial weight of an evaluation factor can be understood as the degree of influence of the evaluation factor on the grade assessment of the entity area, or as its importance to the grade assessment. For example, in a fire safety assessment, the initial weight of an evaluation factor can be understood as the importance of the fire hazard to fire safety.

[0145] For example, taking the two evaluation factors of whether the building fire protection partitions are maintained in compliance with fire protection standards and whether the secondary decoration inside the building is in compliance with fire protection standards as examples, the initial weight of the former is 0.05 and the initial weight of the latter is 0.03, which means that the importance of the former to fire safety is higher than the importance of the latter to fire safety.

[0146] It can be understood that the greater the initial weight, the higher the importance, and conversely, the smaller the initial weight, the lower the importance.

[0147] After constructing the association relationship, the internal logical association between the evaluation factors can be portrayed, so as to achieve a hierarchical division of the impact of the evaluation factors on the target business. For example, the more other platform factors an evaluation factor is associated with, the more evaluation factors that have direct and indirect impacts on it, and the more other evaluation factors that it can directly and indirectly affect, then the evaluation factor is characterized as a factor that has an important impact on the evaluation of the target business. After being characterized through the association relationship, a more accurate mutual influence relationship between the evaluation factors can be obtained, and thus according to the more accurate mutual influence relationship, more accurate evaluation parameters can be obtained.

[0148] In some examples, when constructing the association relationship between evaluation factors, influence relationships input for multiple evaluation factors may be received, where the influence relationship is used to characterize that the evaluation factors have a direct association; and based on the influence relationship, the association relationship may be constructed.

[0149] In this example, the influence relationship can be input by the user for multiple evaluation factors, which represents the direct influence between the evaluation factors. For example, if evaluation factors C and D directly influence evaluation factor A, then there is a direct influence relationship between evaluation factors C and A, and between evaluation factors A and D.

[0150] Taking fire safety assessment as an example, the evaluation factors obtained are shown in Table 1 below. The influence relationship between the evaluation factors is also shown in Table 1 below. Table 1 shows the evaluation factors and other evaluation factors that have an influence relationship with the evaluation factors.

[0151] Table 1 - Evaluation factors and impact relationship diagram

[0152] Since the direct impact relationship is the most direct correlation between evaluation factors, and there are indirect impact relationships under the direct impact relationship of multiple evaluation factors, it is necessary to construct a relationship including indirect and direct correlations based on the direct impact relationship between the evaluation factors.

[0153] When constructing an association relationship including direct associations and indirect associations based on a direct influence relationship, it can be implemented based on an association matrix.

[0154] In specific implementation, the association matrix A (adjacency matrix) between the evaluation factors can be further derived based on the influence relationship table between the above-mentioned evaluation factors (such as Table 1). The association matrix is ​​subjected to power operations according to Boolean algebra, and after several iterations, the reachable matrix M is obtained. Then, a hierarchical analysis of the hidden danger factors is performed based on the reachable matrix. The reachable set and the predecessor set (precursor set) are used to determine the level to which the hidden danger factors belong, thereby constructing the association relationship of all factors.

[0155] The correlation matrix A can be constructed according to the above formula (1):

[0156] The reachability matrix M can be obtained by the following formula (2):

[0157] M=(A+I) n+1 =(A+I) n ≠(A+I) n-1 (I is the identity matrix) Formula (2);

[0158] The reachable set constructed is P(S i )={S j |m ij =1}i=1,2,3…n;

[0159] The constructed precedent set is Q(S i )={S j |m ji =1}i=1,2,3…n;

[0160] Among them, if P(S i )∩P(S i )=P(S i ), then S i It is the current superlative element;

[0161] In the above formula, D i Denotes the evaluation factor i, D j Indicates the evaluation factor j, m ij =1 indicates that the occurrence of the event corresponding to evaluation factor i has an impact on the occurrence of the event corresponding to evaluation factor j, that is, evaluation factor i is the antecedent of evaluation factor j, m ji =1 indicates that the occurrence of the event corresponding to evaluation factor j has an impact on the occurrence of the event corresponding to evaluation factor i, that is, evaluation factor j is the antecedent of evaluation factor i.

[0162] For example, taking seven evaluation factors as an example, the calculation process is as follows:

[0163] It is assumed that the correlation between the seven evaluation factors is shown in Table 2 below:

[0164] Table 2 - Correlation between seven evaluation factors

[0165] The adjacency matrix (incidence matrix) is as follows, denoted as A:

[0166] Let the identity matrix I be:

[0167] Add the adjacency matrix A to the identity matrix I:

[0168] The reachable matrix is ​​calculated as (A+I) multiplied by itself (i.e. matrix multiplication) until it stops changing: M=(A+I) n+1 =(A+I) n ≠(A+I) n-1

[0169] The calculated reachability matrix M is shown in Table 3 below:

[0170] Table 3 - Reachable Matrix M Table

[0171] According to the reachability matrix, the reachable set and the antecedent set (predecessor set) are sorted as shown in Table 4 below:

[0172] Table 4 - Reachable Set and Predecessor Set Table

[0173] Thus, according to the above process, the correlation between the various evaluation factors can be obtained based on the influence relationship (direct correlation relationship) between the evaluation factors;

[0174] For example, referring to FIG3 , FIG3 takes Table 1 as an example and shows a schematic diagram of the association relationship between the constructed evaluation factors. From FIG3 , the inherent logical connection between the various evaluation factors can be intuitively seen.

[0175] In some examples, after obtaining the association, initial weights can be set for each evaluation factor based on the association. This initial weight can be understood as the probability that the evaluation factor will lead to the occurrence of the target business, called the occurrence probability. For example, in a fire safety assessment, the evaluation factor is fire water supply facilities. Its initial weight is assumed to be 0.1, indicating that if a problem with the fire water supply facilities occurs, there is a 10% probability of causing a fire.

[0176] One way to set initial weights is to display the associations and then accept the user's input for each evaluation factor. Another way to set initial weights is to assign an initial weight to an evaluation factor based on the number of other evaluation factors associated with it. For example, as shown in Figure 3, the number of evaluation factors associated with fire is the largest, so the initial weight can be set to 0.10.

[0177] Among them, when setting the initial weight corresponding to the number according to the number of associated relationships, the target evaluation factor that has an associated relationship with the largest number of evaluation factors can be determined first, that is, the number of evaluation factors affected by the target evaluation factor is the largest, and the initial weight of the target evaluation factor is set according to the number of evaluation factors affected by the target evaluation factor. Then, according to the initial weight of the target evaluation factor, the initial weights of other evaluation factors are determined. Of course, it can be understood that the fewer the number of associated evaluation factors, the smaller the initial weight. Among them, the initial weights of other evaluation factors except the target evaluation factor can be smaller than the target evaluation factor.

[0178] By adopting this method of setting the initial weight according to the quantity, the information processing platform can automatically set the initial weight of each evaluation factor according to the correlation relationship without the need for manual setting, further avoiding human participation and thus improving the degree of automated management and control.

[0179] Next, it is necessary to obtain the evaluation parameters of each evaluation factor based on the initial weight of each evaluation factor.

[0180] In one case, the evaluation parameter may be the initial weight, and in another case, the evaluation parameter may be the weight obtained by further adjusting the initial weight.

[0181] The initial weight can be a value between 0 and 1, and the evaluation parameter can be a percentage value of the initial weight. For example, if the initial weight is 0.05, the evaluation parameter is 5. Of course, the initial weight can also be a percentage value, such as 5, and the evaluation parameter can also be a percentage value. There is no special limitation here.

[0182] Among them, in the method of adjusting the initial weights to determine the evaluation parameters corresponding to each preset dimension, one method may be to set the influence parameters corresponding to each evaluation factor, and then adjust the initial weights based on the influence parameters, and the influence parameters are used to characterize the influence of an evaluation factor on an evaluation factor with an associated relationship; another method is to perform multiple rounds of adjustments on the initial weights of the evaluation factors based on randomly generated random numbers. In the multiple rounds of adjustments, the initial weights can be adjusted based on the influence parameters. In this way, in each round of adjustment, multiple evaluation factors obtain an adjusted initial weight. Therefore, after multiple rounds of adjustment, each evaluation factor has multiple adjusted initial weights. Based on the multiple adjusted initial weights, the final evaluation parameters of an evaluation factor can be obtained.

[0183] In a specific implementation, in one embodiment, referring to FIG. 4 a , a schematic flow chart of the steps for adjusting the initial weights is shown. As shown in FIG. 4 a , the following steps may be specifically included:

[0184] Step S401: determining an impact parameter of a first evaluation factor on a second evaluation factor having an associated relationship;

[0185] The influence parameter is used to characterize the degree of influence of the first evaluation factor on the second evaluation factor; wherein the first evaluation factor is any evaluation factor among the multiple evaluation factors.

[0186] In the present disclosure, the degree of influence of a first evaluation factor on a second evaluation factor associated with the first evaluation factor includes the magnitude of influence and the direction of influence, wherein the direction of influence indicates whether it is a positive influence or a negative influence.

[0187] As shown in Table 5 below, it shows a schematic diagram of the setting of the influencing parameters, where K represents the direction of influence. A positive value represents a positive influence, indicating that when the event represented by the evaluation factor occurs, the probability of the event represented by another evaluation factor with which it is associated will increase; a negative value represents a negative influence, indicating that when the event represented by the evaluation factor occurs, the probability of the event represented by another evaluation factor with which it is associated will decrease; S represents the size of the influencing parameter. The larger the value, the greater the degree of influence.

[0188] Table 5 - Influencing parameter settings

[0189] Among them, the influence parameter of the evaluation factor can be determined according to the influence of the evaluation factor on other evaluation factors. Among them, for an evaluation factor, when it has an association relationship with different evaluation factors, its influence parameters on different evaluation factors may be different. For example, for evaluation factor A, it has an association relationship with evaluation factors B and C, then the influence parameter of evaluation factor A on evaluation factor B may be different from the influence parameter of evaluation factor A on evaluation factor C.

[0190] That is to say, the first evaluation factor may have different influence parameters for different second evaluation factors. Referring to Figure 4b, taking fire safety as an example, a schematic diagram of the setting of the influence parameters of 23 evaluation factors is shown. As shown in Figure 4b, the influence parameters can be expressed in the same parameter representation as the initial weights, such as using numerical values ​​between 0 and 1. Among them, when setting the influence parameters, they can be set in the manner of Table 5, that is, according to the other evaluation factors affected by the evaluation factor, according to several preset influence parameters, the influence parameters of the evaluation factor on other evaluation factors can be set. As shown in Figure 4b, the influence parameters can be set to 1, 0.8, 0.2 or 0.5.

[0191] It is understood that the influencing parameter can be 0 or 1.

[0192] Step S402: Based on the influencing parameter, the initial weight of the second evaluation factor is adjusted.

[0193] Step S403: Based on the adjusted initial weights, determine the evaluation parameters corresponding to the preset dimensions.

[0194] Among them, when adjusting the initial weight of the second evaluation factor, since the second evaluation factor is affected by the first evaluation factor, the initial weight of the second evaluation factor will be fine-tuned according to the influencing parameter. For each evaluation factor, the initial weight of each other evaluation factor that has an associated relationship with the evaluation factor can be adjusted.

[0195] In one example, the initial weight can be adjusted according to the cross-influence empirical formula (3): j =P j +KS ij (P j -1)P j ,(i=1,2,3…n)Formula (3)

[0196] In formula (3), P j To evaluate the factor D i Before it happens, evaluate factor D j Probability of occurrence; P′ j For event D i After the occurrence, evaluate the factor D j Probability value of occurrence; KS ij To evaluate the factor D i Evaluation factor D j The influencing parameters, where K is the influencing direction, S ij is the degree of influence, S ij The values ​​of are given in Table 5 above.

[0197] Among them, the evaluation factor D j The probability of occurrence is D j Initial weight, evaluation factor D j The probability of occurrence is D j The initial weight of .

[0198] In practice, an evaluation factor may be adjusted by the influencing parameters of multiple evaluation factors. In this case, the initial weight of an evaluation factor adjusted by the influencing parameters of multiple evaluation factors can be calculated. In this way, an evaluation factor can obtain multiple adjusted initial weights. In practice, the average of multiple adjusted initial weights can be used as the final adjusted weight of the evaluation factor.

[0199] For example, as shown in Figure 4b, for the evaluation factor "daily fire inspection", it is affected by the evaluation factors D1-D4, so it will correspondingly obtain 4 weights adjusted by the influencing parameters of the evaluation factors D1-D4. The average of the 4 weights can be used as the final adjusted initial weight of the evaluation factor "daily fire inspection".

[0200] This initial weight adjustment method can achieve fast adjustment and high computational efficiency.

[0201] In a specific implementation, as in another embodiment, referring to FIG5 , a schematic diagram of a process for adjusting the initial weights in multiple rounds is shown. As shown in FIG5 , the initial weights of multiple evaluation factors can be adjusted in sequence, wherein, when each evaluation factor is adjusted, the initial weights of other evaluation factors associated with the evaluation factor are adjusted based on the random number corresponding to the evaluation factor;

[0202] Then, the steps of adjusting the initial weights of the multiple evaluation factors in sequence are repeated for multiple rounds to obtain the adjusted initial weights of the multiple evaluation factors corresponding to the multiple rounds of adjustments;

[0203] Then, based on the adjusted initial weights of the multiple evaluation factors respectively corresponding to the multiple rounds of adjustments, the evaluation parameters respectively corresponding to the multiple preset dimensions are obtained.

[0204] In each round of adjustment, multiple evaluation factors are adjusted in turn. Assuming there are 23 evaluation factors, 23 adjustments will be made. In each adjustment, the initial weights of other evaluation factors that are associated with the evaluation factor will be adjusted based on the initial weight of the current evaluation factor and the size of the random number.

[0205] Among them, assuming that the current evaluation factor to be compared with the random number is the third evaluation factor, when adjusting the third evaluation factor, if it is necessary to adjust the initial weight of the fourth evaluation factor associated with the third evaluation factor, the adjustment will be made on the initial weight of the fourth evaluation factor after the last adjustment, wherein the current initial weight of the third evaluation factor is also its initial weight after the last adjustment.

[0206] For example, the third evaluation factor is evaluation factor A, and the initial weight of evaluation factor A is 0.5. The evaluation factors associated with it are B and C. In the last adjustment of this round of adjustment, the initial weight of evaluation factor A was adjusted from 0.5 to 0.47. The adjustment to 0.47 was due to other evaluation factors that have an impact on evaluation factor A. Therefore, during this adjustment, its random number can be compared with 0.47. Then, based on the comparison results, when it is determined that the associated evaluation factors B and C need to be adjusted, adjustments will be made to the initial weights of evaluation factors B and C after the last adjustment.

[0207] Among them, after adjusting multiple evaluation factors, the next round of adjustments can be carried out. It should be noted that in the next round of adjustments, adjustments are made to the initial weights of each evaluation factor, that is, each round of adjustments is carried out from the initial state. For example, after the first round of adjustment of evaluation factor A, its initial weight is 0.45, then in the next round of adjustment, the initial weight returns to the initial 0.5, and the next round of adjustment begins.

[0208] As shown in Figure 5, in the process of adjusting the initial weights of other evaluation factors that are associated with each evaluation factor based on the random number corresponding to the evaluation factor, the initial weights of other evaluation factors can be adjusted when the initial weight of the evaluation factor is greater than the random number; when the initial weight of the evaluation factor is not greater than the random number, the initial weights of other evaluation factors after the last adjustment are retained.

[0209] Among them, the random number can be understood as a randomly generated initial weight, which actually represents the random occurrence probability of the event corresponding to the evaluation factor. When the initial weight of the evaluation factor is greater than the random number, it means that the event represented by the evaluation factor will occur, which will affect the events corresponding to other platform factors. Therefore, the initial weights of other platform factors need to be adjusted; when the initial weight of the evaluation factor is not greater than the random number, it means that the event represented by the evaluation factor will not occur, and will not affect the events corresponding to other platform factors. Therefore, the current initial weights of other platform factors can be kept unchanged.

[0210] As shown in FIG5 , in some examples, when adjusting the initial weights of other evaluation factors associated with the evaluation factor, the adjustment can be made based on the influence parameters of the evaluation factors. Specifically, reference can be made to the process shown in FIG4 above. During implementation, based on the random number corresponding to the evaluation factor, when adjusting the initial weights of the evaluation factors associated with the evaluation factor, the influence parameters of the evaluation factor on the associated evaluation factors can be determined, and based on the influence parameters, the initial weights of the evaluation factors associated with the evaluation factor can be adjusted.

[0211] As described in the above embodiment, the impact parameter can represent the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor, including the magnitude and direction of the influence. The specific adjustment process can be carried out with reference to formula (3).

[0212] For example, as shown in FIG5 , the adjustment of the initial weight in this manner is described as follows:

[0213] a. First, determine the number of simulations N, which indicates that N rounds of adjustments are required, where N is an integer greater than 1. Then, determine the initial weights of each evaluation factor and the influencing parameters between the evaluation factors.

[0214] When the first round of adjustment begins, one evaluation factor Di is randomly selected from n evaluation factors to start simulation calculation; n is a positive integer greater than or equal to 1, where N and n are different values.

[0215] b. Use a random number generator or random number table to obtain a random number, compare this random number with the initial weight of Di, and determine whether Di occurs. If the simulation results show that Di does not occur, the initial weights of the other evaluation factors remain unchanged. If the simulation results show that Di occurs, the initial weights of the evaluation factors associated with Di are adjusted according to the aforementioned formula (3).

[0216] c. Randomly select an evaluation factor Dj from the remaining undrawn evaluation factors and compare the newly obtained random number with the initial weight of Dj. It should be noted that if the initial weight of Dj has been adjusted, it is necessary to use the adjusted initial weight and repeat step b. If Dj occurs, the initial weight of the evaluation factor associated with Dj is adjusted.

[0217] d. Continue the simulation process until all n evaluation factors have been sampled. This process is called a round of adjustment. In a round of adjustment, each evaluation factor has its weight adjusted by the interaction of other evaluation factors.

[0218] e. Restore the initial weights of all evaluation factors to their initial state and begin the next round of adjustments from step a. After several rounds, say 1,000 or more, calculate the weights of each evaluation factor after multiple rounds of adjustments. The resulting weights are the final weights of each evaluation factor under the cross-influence.

[0219] Accordingly, in this multi-round adjustment approach, since each round of adjustment yields an adjusted initial weight, each evaluation factor will have multiple adjusted initial weights after multiple rounds of adjustment. In practice, the average of the multiple adjusted initial weights can be used as the final adjusted weight for the evaluation factor. Subsequently, the final evaluation parameter for the evaluation factor can be determined based on the final initial weight of each evaluation factor.

[0220] In some examples, to ensure the accuracy of the evaluation parameters, the Markov chain steady state can be used to solve the initial weight in the steady state, and the initial weight in the steady state can be used as the evaluation parameter corresponding to the evaluation factor.

[0221] In a specific implementation, referring to FIG6 , a flow chart of steps for solving the evaluation parameters in the case of multiple rounds of adjustment is shown. As shown in FIG6 , the steps may include:

[0222] Step S601: constructing a cross-influence probability matrix based on the influence parameters between the evaluation factors having correlation relationships;

[0223] Step S602: performing multiple iterative preset operations on the cross-influence probability matrix and the adjusted initial weights corresponding to the multiple evaluation factors in the multiple rounds of adjustments until a preset end condition is met;

[0224] Step S603: Based on the cross-influence probability matrix when the preset end condition is reached, obtaining evaluation parameters corresponding to each of the plurality of preset dimensions.

[0225] In step 601, the evaluation factors with an associated relationship have influence parameters. The setting of the influence parameters can be shown in Figure 3. In practice, a cross-influence probability matrix can be constructed based on the influence parameters between the evaluation factors with an associated relationship. Each value in the cross-influence probability matrix represents the degree of influence between the evaluation factor Di and the evaluation factor Dj. The cross-influence probability matrix can be shown with reference to the above-mentioned adjacency matrix A. Unlike the adjacency matrix A, each value in the cross-influence probability matrix corresponds to an influence parameter.

[0226] In step S602, the cross-influence probability matrix and the final initial weights of each of the multiple evaluation factors can be iteratively performed multiple preset operations. The preset operation can be a matrix multiplication operation, that is, the final initial weights of each of the multiple evaluation factors can be taken as a one-dimensional matrix, and the matrix can be iteratively multiplied with the cross-influence probability matrix multiple times until the preset end condition is reached.

[0227] The preset end condition may be: after the cross-influence probability matrix is ​​multiplied by the final initial weights of the multiple evaluation factors for a sufficient number of iterations, the values ​​of each row are equal; wherein the one-dimensional matrix used for the next multiplication is the one-dimensional matrix obtained after the previous multiplication with the cross-influence probability matrix. Specifically, the following formula (4) may be referred to: π=π0P n =π0P n+1 =π0P n+2 Formula (4)

[0228] Wherein, n is a positive integer greater than or equal to 1, π0 is a one-dimensional matrix composed of the final initial weights of multiple evaluation factors, P is the cross-influence probability matrix, and π is the Markov stable state.

[0229] As shown in formula (4), when multiplying for the first time, the final initial weights of multiple evaluation factors are multiplied with the cross-influence probability matrix, and the multiplication result is a one-dimensional matrix, denoted as π0P 1 ; Then, the one-dimensional matrix π0P 1 Multiply it again with its cross-influence probability matrix p to get a one-dimensional matrix π0P 2 , then, π0P 2 Multiplying by p, we get π0P 3 , repeating this way, when the above formula (4) is satisfied, it can be said that the preset end condition has been reached, and the operation is terminated, and the one-dimensional matrix π0P at the end of the operation is saved n , the one-dimensional matrix π0P n This is the initial weight distribution that ultimately achieves the steady-state characteristics of the Markov chain.

[0230] Finally, the initial weight distribution that achieves the steady-state characteristic of the Markov chain can be converted into a percentage score. A Markov chain stationary state is defined as: a non-periodic Markov chain with a transition probability matrix P, where any two states are connected, and after enough iterations, a stable state exists, where the values ​​in each row of the two matrices are equal after multiplying them by themselves enough times.

[0231] In some embodiments, if the preset end condition is still not reached after multiplying by itself enough times, the initial weights of each evaluation factor can be restored to the initial weights set initially, and multiple rounds of initial weight adjustments can be performed again, that is, the process shown in Figure 5 is repeated to obtain the final weights of each evaluation factor, and then the steady-state characteristics of the Markov chain are calculated until the steady-state characteristics of the Markov chain are reached.

[0232] When this embodiment is adopted, since multiple rounds of adjustments are performed when adjusting the initial weights of the evaluation factors, the adjustment accuracy and stability of the initial weights can be improved when the evaluation factors have mutual influence, thereby improving the accuracy of the evaluation parameters.

[0233] As described above, the evaluation parameter can be the percentage value of the final initial weight of the evaluation factor. Then, through the above implementation, the evaluation parameter corresponding to each evaluation factor can be obtained. Since one preset dimension corresponds to one evaluation factor, the evaluation parameter corresponding to the evaluation factor is the evaluation parameter corresponding to the preset dimension. As described above, the evaluation parameter can be understood as the benchmark score of the preset dimension where the evaluation factor is located. In this way, according to the dimensional information of the preset dimension, it can be deducted on the basis of the benchmark score to obtain the quantitative score value of the preset dimension. The sum of the quantitative score values ​​of multiple preset dimensions can be used as the basis for determining the grading parameter.

[0234] For example, taking fire safety assessment as an example, referring to Table 6 below, Table 6 shows a schematic table of the adjusted initial weights of each assessment factor and the assessment parameters:

[0235] It should be noted that the table 6 can be stored and used as evaluation parameters for different entity areas on the target business. That is, multiple entity areas can share the same set of evaluation parameters for the target business to evaluate their levels on the target business.

[0236] Among them, Table 6 is only an example and does not represent a limitation of this application. In practice, the evaluation parameters can also be formulated under other scoring standards, such as a 60-point system, an 80-point system, a 50-point system, etc. In practice, they can be set according to user needs. It should be pointed out that the percentage system means that the sum of the evaluation parameters of all evaluation factors is 100.

[0237] The corrected weights in Table 6 are the adjusted initial weights described in this application, which are the weights adjusted by the influencing parameters.

[0238] Table 6 - Adjusted initial weights of various evaluation factors and evaluation parameters

[0239] It should be noted that the table 6 can be stored and used as evaluation parameters for different entity areas on the target business. That is, multiple entity areas can share the same set of evaluation parameters for the target business to evaluate their levels on the target business.

[0240] Specifically, multiple dimensional information can be quantified first to obtain the quantitative value corresponding to each dimensional information; and based on multiple evaluation parameters and multiple quantitative values, the quantitative score values ​​corresponding to each of the multiple evaluation factors can be determined; then, based on each quantitative score value, the grading parameters can be determined.

[0241] Quantization can refer to converting dimensional information into numerical values, that is, converting dimensional information into numerical information. Specifically, if the dimensional information includes text information, quantization can be performed based on a preset conversion relationship between multiple text words and numerical values. For example, if the dimensional information includes status information of ventilation facilities, where the status information is a code indicating good ventilation, the code can be converted into a corresponding numerical value based on the numerical value corresponding to good ventilation, thereby achieving quantification. If the dimensional information is a description of measures taken for the target business, when entering this business information, the user can be required to enter numerical information, such as the number of fire drills held, so that the number can be directly extracted from the dimensional information and quantified.

[0242] Among them, the quantization value can be a value from 0 to 1, including 0 and 1. If the dimension information is a number, it can be normalized to obtain a quantization value between 0 and 1. For example, when a number is extracted from the dimension information as mentioned above, the number can be normalized.

[0243] When determining the quantitative scoring values ​​corresponding to multiple evaluation factors based on multiple evaluation parameters and multiple quantitative values, for each preset dimension, the evaluation parameter of the preset dimension and the quantitative value under the preset dimension can be operated to obtain the quantitative scoring value. The operation can be a multiplication operation. For example, if the evaluation parameter is 3 and the quantitative value is 0.8, then its quantitative scoring value is 2.4.

[0244] Thus, according to the above process, the quantitative scores corresponding to the various evaluation factors can be obtained. Then, the sum of the quantitative scores can be determined to obtain a total quantitative score. Then, the preset score interval in which the total quantitative score falls is determined, and the grading parameter corresponding to the preset score interval is used as the grading parameter corresponding to the physical area. This grading parameter can be used to represent the risk level of the physical area with respect to the target business. The lower the risk level, the higher the grade of the physical area, and the lower the risk it has with respect to the target business.

[0245] It is understandable that: in some cases, the higher the total quantitative score value, the higher the grading parameter and the lower the risk level; the lower the total quantitative score value, the lower the grading parameter and the higher the risk level;

[0246] Of course, in some other cases, other ways of determining grading parameters are not ruled out. For example, the higher the total quantitative score value, the lower the grading parameter and the higher the risk level; the lower the total quantitative score value, the higher the grading parameter and the lower the risk level.

[0247] Referring to Table 7 below, taking fire safety assessment as an example, the grading parameters corresponding to different preset scoring intervals are shown.

[0248] Table 7 - Grading parameters corresponding to different preset scoring intervals

[0249] In some embodiments, after obtaining the quantitative scoring values ​​corresponding to multiple evaluation factors, the evaluation factors with larger differences can be determined based on the differences between the quantitative scoring values ​​of each evaluation factor and the evaluation parameters. The evaluation factors with larger differences can be understood as evaluation factors that have a greater negative impact on the classification of the target business. In practice, it is necessary to rectify the preset dimension where the evaluation factor is located, such as rectifying the various facilities under the preset dimension, so that the working conditions of these facilities can be restored to a good level.

[0250] In specific implementation, the difference between the evaluation parameter and the corresponding quantitative rating value can be determined; based on the difference, at least one target evaluation factor is determined from multiple evaluation factors; and recommendation information corresponding to each target evaluation factor is output.

[0251] In some examples, the difference between the evaluation parameter and the corresponding quantitative score value can be the difference between the index values. Since the evaluation parameter is a baseline score and the quantitative score value is a score value obtained by evaluating the dimensional information, the difference between the two can reflect the effectiveness of the working status / measures of the facility belonging to the preset dimension. The larger the difference, the worse the working status / effectiveness, and the more rectification is needed in practice.

[0252] The target evaluation factor may be an evaluation factor whose difference is greater than or equal to a preset difference, and the preset difference may be preset, for example, to 1 or 2. Each evaluation factor is a preset dimension, and recommendation information corresponding to an unqualified quantitative rating value may be pre-stored for each preset dimension. After determining the target evaluation factor, the recommendation information corresponding to the target evaluation factor may be directly obtained, and then the recommendation information may be sent to a client in the physical area so that the client in the physical area displays the recommendation information.

[0253] In some examples, when the grading parameters do not reach the preset grading parameters, the above-mentioned steps of determining the difference between the evaluation parameters and the corresponding quantitative rating values ​​can be performed; based on the difference, at least one target evaluation factor is determined from multiple evaluation factors, and recommendation information corresponding to each target evaluation factor is output. In this way, when the evaluation level of the entity area is not high, the preset dimensions whose quantitative rating values ​​do not meet the standards can be rectified. Among them, the preset grading parameters can be pre-set, for example, as shown in Table 3, they can be set to 80 or 85. Of course, this is only an exemplary description. In practice, it can be set according to the specific requirements of the entity area for the target business.

[0254] In some examples, the target evaluation factor can be comprehensively determined based on the influence parameters between the evaluation factors and the difference between the quantitative score value of the evaluation factor and the evaluation parameters. The larger the influence parameter, the higher the degree of influence of the evaluation factor on other evaluation factors. If the evaluation factor with a larger influence parameter, such as an evaluation factor that exceeds the preset influence parameter, has a difference exceeding a difference threshold, then the evaluation factor can be used as the target evaluation factor.

[0255] It should be noted that when the target evaluation factor is jointly determined based on the influencing parameters and the difference, the difference threshold can be smaller than the above-mentioned preset difference, that is, smaller than the benchmark difference based on which the target evaluation factor is determined solely based on the difference.

[0256] Correspondingly, in some other embodiments, if the grading parameters are lower than the preset grading parameters, it is generally necessary to promptly rectify the physical area. In this case, the information collection equipment under the preset dimensions can be controlled to output alarms, so as to carry out targeted on-site alarms and rectifications on facilities that fail the assessment, so as to improve the level of automation in the management and control of the physical area.

[0257] In a specific implementation, when the grading parameter is lower than the preset grading parameter, the target preset dimension in which the difference between the quantitative score value and the evaluation parameter is greater than the preset difference can be determined, and the target information collection device can be controlled to output a warning message;

[0258] Among them, the target information collection device is used to collect business information of the target preset dimensions.

[0259] Specifically, each type of business information can correspond to an information collection device, which can be a sensor, computer, camera, tablet, etc. Computers and tablets can be used to input information related to the measures taken to execute the target business. Sensor-type target information collection devices can be equipped with an alarm module, which can be an audible or visual alarm, such as a buzzer.

[0260] In practice, the information processing platform may send an alarm instruction to the target information collection device, and the target information collection device may generate an alarm, such as a buzzer, after receiving the alarm instruction.

[0261] It should be noted that, taking fire safety assessment as an example, the warning information output by the target information collection device can be different from the warning used by the fire department to avoid user misunderstanding of the alarm, so as to accurately distinguish between the fire alarm and the rectification alarm disclosed in this disclosure.

[0262] By adopting this implementation scheme, it is possible to automatically alarm the facilities in the preset dimensions of the physical area that have failed the evaluation or have a low evaluation according to the grading parameters, so as to inform the construction personnel to carry out timely rectification and maintenance to eliminate hidden dangers, thereby avoiding risks in the physical area for the target business.

[0263] In other embodiments, it is generally necessary to continuously monitor the status of the physical area in the target business. For example, in a fire safety assessment, the fire safety of a building needs to be regularly assessed. In each assessment, the method of the above embodiment can be used to obtain a classification parameter. In this way, the classification parameters corresponding to the physical area in multiple different time periods can be obtained; and based on the classification parameters corresponding to the multiple different time periods, the classification statistics of the physical area can be output to indicate the changes in the classification of the physical area in different time periods of the target business.

[0264] The time periods in this embodiment must be distinguished from the preset time periods used for evaluating target services as described above. Specifically, the time periods in this embodiment refer to the grading determination for the same grading target within the target service. The grading parameters corresponding to multiple different time periods are the grading parameters corresponding to the same grading target. This allows for grading statistics to be generated based on the same benchmark.

[0265] Of course, going further, when the quantitative score value corresponding to each evaluation factor is obtained, since the evaluation parameters of the evaluation factor can remain unchanged within a certain period, the change in the quantitative score value corresponding to the evaluation factor can reflect the status change of the facilities in the physical area and the continuity of the implementation measures. Therefore, evaluation factor statistical information reflecting the change in the quantitative score value corresponding to each evaluation factor can be generated. The evaluation factor statistical information, such as the above-mentioned hierarchical statistical information, can be in the form of a chart, such as a bar chart, pie chart, line chart, heat map, etc.

[0266] In practice, based on hierarchical statistical information and evaluation factor statistical information, the entity area's continuous control over the target business can be monitored to obtain its weak dimensions in the target business and make targeted rectifications to the weak dimensions.

[0267] The technical solution of the embodiment of the present disclosure has the following advantages:

[0268] 1. By building relationships between multiple evaluation factors, we accurately depict the explanatory model of factors that influence the evaluation of entity regions in target businesses, making the evaluation factor hierarchy clearer and more intuitive, and improving the accuracy of scoring;

[0269] 2. Adjust the initial weights by using the influencing parameters between the correlated evaluation factors. During this process, corrections can also be made based on the Markov chain to obtain quantitative analysis results of the evaluation factors, providing a more accurate evaluation basis for the quantitative evaluation of the target business.

[0270] 3. Based on the actual business information of the physical area and the evaluation parameters of the evaluation factors, the physical area is evaluated, and according to the evaluation results, the information collection equipment in the physical area is controlled to feedback the results in real time. This can improve the automation level of the management and control of the physical area and enhance the real-time performance, thereby helping the physical area to eliminate hidden dangers in a timely manner and improve its security in the target business.

[0271] The following is an illustrative example of the information processing method disclosed herein:

[0272] As shown in Figure 1, taking fire safety assessment as an example, it includes:

[0273] S1: First, determine multiple assessment factors for building fire safety.

[0274] Specifically, it can obtain assessment factors related to fire safety from the database. The multiple assessment factors can be divided into 4 categories with a total of 23 factors, as shown below:

[0275] The first category: building fire protection management. The main evaluation indicator is whether there are changes to building fire protection facilities that have been approved by legal regulations. The evaluation factors include: building fire resistance level, decoration status, amount of combustible materials, emergency exits, and unobstructed evacuation routes. These are shown in D1-D4 in Table 1 above.

[0276] The second category: Firefighting facilities and equipment management. Key evaluation factors include equipment integrity and effectiveness, equipment failures, and specifically, the integrity and effectiveness of firefighting systems such as automatic fire alarms, automatic sprinklers, fire hydrants, smoke exhaust systems, and emergency lighting, as well as planned completion of firefighting maintenance. These evaluation factors are listed in Table 1 above, including D5-D10.

[0277] The third category: daily fire management, whose main indicators are whether work is completed as required and whether daily management responsibilities are fulfilled. Examples include fire control room management requirements; completion of fire inspections and patrols; number of fire hazards and timely rectification; all employees' fire education and training, and passing of exams; micro-fire stations fully staffed and equipped; daily duty, daily training, and firefighting and rescue drills; and rapid fire response and containment to prevent escalation and significant damage. These evaluation factors include D11-D22, as shown in Table 1 above.

[0278] The fourth category: fire occurrence. Industry experts set initial parameters based on local standards and judge the fire safety level based on historical fire occurrences. The assessment factors included are D23 shown in Table 1 above.

[0279] S2: Construct the correlation between the assessment factors, such as constructing the risk assessment factor explanatory model shown in Figure 3.

[0280] The connection relationship between the evaluation factors may be received, and the connection relationship may indicate the interaction relationship between the evaluation factors. Specifically, the connection relationship may be given by an expert.

[0281] According to the connection relationship between the above-mentioned evaluation factors, the connection relationship can reflect the direct influence relationship between the evaluation factors, which is shown in the above-mentioned Table 1.

[0282] Furthermore, the association matrix (adjacency matrix) between the evaluation factors is obtained, and the association matrix is ​​subjected to power operations according to Boolean algebra, and the reachable matrix M is obtained after several iterations.

[0283] M=(A+I) n+1 =(A+I) n ≠(A+I) n-1 (I is the identity matrix)

[0284] Hierarchical analysis of potential hazards is performed based on a reachability matrix, using reachable sets and antecedent sets (precursor sets). The reachable set includes direct and indirect relationships between assessment factors, while the antecedent set includes assessment factors that have a positive direct impact on an assessment factor. For example, if the occurrence of assessment factor A leads to the occurrence of the event represented by assessment factor B, then assessment factor A is included in the antecedent set.

[0285] Based on the above reachable sets and antecedent sets, an explanatory structural model of all factors is constructed.

[0286] The hierarchical division process is as follows: Based on the reachability matrix M, first find the highest-level elements that meet the above conditions, remove these elements from the reachability matrix, and then find the highest-level elements in the new matrix. This process is repeated layer by layer to divide the evaluation factors into different levels. The explanatory structural model constructed in this example is shown in Figure 3.

[0287] S3: Output the explanatory structural model, and then receive the initial weights and influence parameters input for each evaluation factor in the explanatory structural model.

[0288] The influencing parameters of each evaluation factor can be shown in FIG4b , and the values ​​of the initial weights can be shown in Table 3 above.

[0289] It can be understood that according to the mechanism of fire occurrence, the evaluation factors can be divided into three categories: direct factors, indirect factors, and deep factors.

[0290] Direct factors are the direct factors that lead to fire accidents, such as fire protection zones, facility integrity, fire hazards, etc.

[0291] Indirect factors refer to reducing the potential possibility of fire from the source, such as whether the secondary decoration meets the standards, the implementation of the fire safety responsibility system, fire safety system and operating procedures, fire drills, micro fire station management, etc.

[0292] The deeper factor lies in improving the fire safety awareness of the unit personnel, such as: the legality of the building, whether fire extinguishing and emergency evacuation plans are prepared, and whether employees receive regular fire safety knowledge training.

[0293] In this way, after constructing the explanatory structural model, we can depict the deeper logical connections between the evaluation factors, thereby accurately obtaining the evaluation parameters.

[0294] S4: Calculation of evaluation parameters for evaluation factors

[0295] Since various events (events represented by evaluation factors) have an impact on each other, in order to accurately obtain the evaluation parameters, the initial weights of the evaluation factors can be adjusted multiple times based on the impact parameters. The steps are as follows:

[0296] Step a: Randomly select an evaluation factor from n evaluation factors to start simulation calculation;

[0297] Step b: Use a random number generator or random number table to obtain a random number, and compare this random number with the randomly selected evaluation factor D i The initial weight is compared to determine the evaluation factor D iIf the simulation results show that the event did not occur, the initial weights of the other evaluation factors remain unchanged. If the simulation results show that the event occurred, the initial weights of the other evaluation factors are adjusted according to formula (1). Among them, the other evaluation factors refer to the factors that are related to the evaluation factor D. i Evaluation factors with associated relationships.

[0298] Step c: Randomly select an evaluation factor from the remaining undrawn evaluation factors, compare the newly obtained random number with the initial weight of the evaluation factor (if the initial weight of the event has been adjusted, the adjusted initial weight needs to be used), and repeat step b. If the event occurs, adjust the initial weights of the other evaluation factors according to formula (1).

[0299] Step d: Continue the simulation process until all n evaluation factors have been sampled. This process is called a simulation round. In a simulation round, each evaluation factor is affected by the interaction of other evaluation factors to obtain a result of "occurrence" or "non-occurrence".

[0300] Step e: Restore the initial weights of all evaluation factors to their initial state and start the next round of simulation from step a. After a number of times (e.g., 1,000 or more), calculate the final initial weight of each evaluation factor.

[0301] Step f: Based on the steady-state properties of the Markov chain, the initial values ​​of the 23 evaluation factors are modified to obtain the adjusted initial weights, resulting in a transition probability matrix P. After sufficiently many iterations of this transition probability matrix P, a stable state is reached, where the values ​​in each row of the probability transition matrix are equal after sufficient iterations. Finally, the transition probability matrix that reaches this stable state is used as the adjusted initial weights corresponding to each evaluation factor.

[0302] S5: Determine the fire safety assessment rating of a designated physical building.

[0303] Through the fire protection Internet of Things platform, business information such as people, things, and objects in fire protection management is obtained, that is, the multiple business information mentioned above in this disclosure.

[0304] The business information is clustered according to the evaluation factors to obtain multiple dimensional information, and then each dimensional information is quantified to obtain a quantized value. Then, based on the evaluation parameters, as shown in Table 3 above, the evaluation parameters are the scores after multiplying the initial weight by 100. The scores are calculated according to the deduction rules, and the upper limit of the deduction is the score of the evaluation factor.

[0305] Add up the quantitative score values ​​corresponding to each evaluation factor, and determine the level of fire safety risk based on the score range in which the total score after the addition falls.

[0306] S6: Recommendations for corrective actions.

[0307] Based on the scores in S5 and the impact of the evaluation factors, provide corrective measures for key non-conforming items.

[0308] For example, in a certain unit's building, personnel inspections revealed that the evacuation passages did not meet fire safety standards, resulting in a 3-point deduction based on the weighted score; the unit did not upload fire extinguishing and emergency response plans to the system for archiving, resulting in a 5-point deduction; according to dynamic monitoring on the fire IoT platform, it was found that the water pressure of the fire hydrants was too low, resulting in a 7-point deduction; and the IoT platform received a residual current alarm (electrical fire monitoring system), resulting in a 5-point deduction. Therefore, the unit's total fire safety risk assessment score = 100-3-5-7-5 = 80 points, with a medium risk level. For the above four unqualified items, matching rectification opinions were searched from the rectification opinion database, and the recommended rectification opinions were: (1) Clear the evacuation passages and keep them unobstructed to meet fire safety standards; (2) Develop a fire extinguishing emergency response plan as soon as possible and upload it to the system for archiving; (3) Check the fire hydrant network system to maintain normal water pressure; (4) Repair the electrical fire system at the corresponding point and repair the fault.

[0309] Based on the same inventive concept, the present disclosure also provides an evaluation parameter output device, which can provide automated and accurate determination of evaluation parameters for the evaluation of physical areas on target businesses, so as to help improve the automation level of evaluation and management of physical areas.

[0310] 7 , a schematic diagram of the framework structure of the evaluation parameter output device is shown. As shown in FIG7 , the device can be integrated into an information processing platform, or can be configured separately in an electronic device and communicated with the information processing platform via the electronic device. The device can specifically include the following modules:

[0311] The factor acquisition module 701 is used to acquire multiple evaluation factors corresponding to the target business in the physical area; wherein one evaluation factor corresponds to a preset dimension of the target business;

[0312] A parameter determination module 702 is used to determine evaluation parameters corresponding to various evaluation factors;

[0313] Output module 703 is used to send the evaluation parameters to the information processing platform, so that the information processing platform determines the grading parameters of the entity area for the target business based on the multiple evaluation parameters and the multiple dimensional information; wherein the grading parameters are used to indicate the level to which the entity area belongs;

[0314] The dimension information is obtained by clustering multiple businesses according to multiple preset dimensions, and the multiple business information at least includes status information of different facilities in the physical area.

[0315] In some examples, the parameter determination module 702 may include the following units:

[0316] A relationship building unit, used to build a correlation relationship between the multiple evaluation factors;

[0317] A weight acquisition unit, configured to output the association relationship and receive an initial weight input for each evaluation factor;

[0318] A parameter determination unit is used to determine the evaluation parameters corresponding to each of the preset dimensions based on the initial weights.

[0319] The process of determining the evaluation parameters may refer to the relevant description in the above-mentioned information processing method, which will not be repeated here.

[0320] In some examples, the apparatus may further include: an influencing parameter determination module and an adjustment module; wherein:

[0321] An impact parameter determination module is used to receive impact parameters input for associated evaluation factors, where the impact parameters are used to represent the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor;

[0322] An adjustment module is used to adjust the initial weights of various evaluation factors based on the influencing parameters;

[0323] The parameter determination unit is specifically used to determine the evaluation parameters corresponding to each preset dimension based on the adjusted initial weights.

[0324] The process of determining the evaluation parameters may refer to the relevant description in the above-mentioned information processing method, which will not be repeated here.

[0325] In some examples, the apparatus may further include: an iterative adjustment module;

[0326] an iterative adjustment module, configured to sequentially adjust the initial weights of a plurality of evaluation factors, wherein, when each evaluation factor is adjusted, the initial weights of evaluation factors associated with the evaluation factor are adjusted based on a random number corresponding to the evaluation factor;

[0327] When adjusting the initial weights of other evaluation factors associated with the evaluation factor, the initial weights of the evaluation factors are adjusted using the influencing parameter determination module and the adjustment module;

[0328] The parameter determination unit is specifically used to obtain evaluation parameters corresponding to multiple preset dimensions based on the adjusted initial weights corresponding to multiple evaluation factors in multiple rounds of adjustments.

[0329] The process of determining the evaluation parameters may refer to the relevant description in the above-mentioned information processing method, which will not be repeated here.

[0330] In some examples, the factor acquisition module is used to obtain multiple evaluation factors from a database corresponding to the target business and to establish association relationships between the multiple evaluation factors.

[0331] The process of constructing the correlation between multiple evaluation factors can refer to the relevant description in the above-mentioned information processing method, and will not be repeated here.

[0332] In some examples, the information processing platform may be an Internet of Things platform, and the output device may be integrated into the information processing platform, or the information processing platform and the output device may be integrated into the Internet of Things platform.

[0333] By adopting the technical solution of the embodiment of the present disclosure, the evaluation parameter output device can provide evaluation parameters of evaluation factors for multiple target businesses. It can be understood that different target businesses may have different evaluation factors. For different evaluation factors, accurate evaluation parameters can still be provided to the corresponding target businesses through the functions of each module in the evaluation parameter output device, so that the information processing platform can automatically complete the level evaluation of the entity area in the target business based on the acquired business information and the evaluation parameters, thereby assisting the automated evaluation and automated management and control of the entity area.

[0334] Based on the same inventive concept, the present disclosure further provides an information processing system, which may be shown in FIG1 , and may specifically include an Internet of Things platform and a plurality of information collection devices connected to the Internet of Things platform; wherein:

[0335] The multiple information collection devices are used to collect business information of the entity area on the target business;

[0336] The Internet of Things platform is used to execute the steps in the information processing method.

[0337] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple, and the relevant parts can be referred to the method embodiment.

[0338] Referring to FIG8 , a schematic diagram of the framework of the information processing system is shown, which includes an information processing platform, an evaluation parameter output device, and multiple information collection devices, with m information collection devices shown in FIG8 . The information processing evaluation and evaluation parameter output device can be integrated into an Internet of Things platform. The evaluation parameter output device is configured to provide the information processing platform with multiple evaluation parameters corresponding to multiple evaluation factors in a target business. The information processing platform is configured to determine the grading parameters of the physical area for the target business based on the business information collected by each information collection device and obtained by the Internet of Things platform, combined with the multiple evaluation parameters.

[0339] Based on the same inventive concept, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the information processing method described in the embodiment when executing the computer program.

[0340] The embodiments of the present disclosure further provide a computer-readable storage medium, which stores a computer program that enables a processor to execute the information processing method as described in the embodiments of the present disclosure.

[0341] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, commodity, or device that includes the element.

[0342] The above is a detailed introduction to the information processing method and device, evaluation parameter output device, system and medium provided by the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present disclosure, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present disclosure.

[0343] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0344] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0345] References herein to "one embodiment," "an embodiment," or "one or more embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Furthermore, please note that instances of the phrase "in one embodiment" do not necessarily all refer to the same embodiment.

[0346] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0347] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present disclosure may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0348] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure.

Claims

1. An information processing method, It is characterized in that The method comprises: Acquire a plurality of business information of the physical area in the target business, wherein the plurality of business information at least includes information for describing the status of different facilities in the physical area; Clustering the plurality of business information according to a plurality of preset dimensions to obtain dimension information corresponding to each of the plurality of preset dimensions; Obtaining evaluation parameters corresponding to each of the plurality of preset dimensions; Based on the multiple evaluation parameters and the multiple dimension information, a grading parameter of the entity area for the target business is determined; wherein the grading parameter is used to indicate the grade to which the entity area belongs.

2. The method according to claim 1, It is characterized in that The obtaining of evaluation parameters corresponding to each of the plurality of preset dimensions includes: Acquire evaluation factors corresponding to each of the plurality of preset dimensions, and construct association relationships between the plurality of evaluation factors; wherein the association relationships include direct association relationships and indirect association relationships; Based on the association relationship, determining the initial weight of each evaluation factor; Based on the initial weights, evaluation parameters corresponding to the preset dimensions are determined.

3. The method according to claim 2, It is characterized in that The constructing of the association relationship between the multiple evaluation factors includes: receiving inputted influence relationships for a plurality of the evaluation factors, wherein the influence relationships are used to represent that the evaluation factors are directly related to each other; Based on the influence relationship, the association relationship is constructed.

4. The method according to claim 2, It is characterized in that The determining, based on the initial weights, the evaluation parameters corresponding to the preset dimensions respectively includes: Determine an influence parameter of a first evaluation factor on a second evaluation factor having an associated relationship, wherein the influence parameter is used to characterize the influence degree of the first evaluation factor on the second evaluation factor; wherein the first evaluation factor is any evaluation factor among the multiple evaluation factors; Based on the influencing parameter, adjusting the initial weight of the second evaluation factor; Based on the adjusted initial weights, the evaluation parameters corresponding to each of the preset dimensions are determined.

5. The method according to claim 2, It is characterized in that The determining, based on the initial weights, the evaluation parameters corresponding to the preset dimensions respectively includes: The initial weights of the plurality of evaluation factors are adjusted sequentially, wherein when each evaluation factor is adjusted, the initial weights of the evaluation factors associated with the evaluation factor are adjusted based on the random number corresponding to the evaluation factor; Repeating the step of sequentially adjusting the initial weights of the multiple evaluation factors for multiple rounds to obtain the adjusted initial weights of the multiple evaluation factors respectively corresponding to the multiple rounds of adjustments; Based on the adjusted initial weights of the multiple evaluation factors respectively corresponding to the multiple rounds of adjustments, the evaluation parameters respectively corresponding to the multiple preset dimensions are obtained.

6. The method according to claim 5, It is characterized in that The adjusting, based on the random number corresponding to the evaluation factor, the initial weight of the evaluation factor associated with the evaluation factor comprises: When the initial weight of the evaluation factor is greater than the random number, adjusting the initial weight of the evaluation factor associated with the evaluation factor; In the case where the initial weight of the evaluation factor is not greater than the random number, the initial weight of the evaluation factor associated with the evaluation factor after the last adjustment is retained.

7. The method according to claim 5, It is characterized in that The adjusting, based on the random number corresponding to the evaluation factor, the initial weight of the evaluation factor associated with the evaluation factor comprises: Determine an impact parameter of the evaluation factor on an associated evaluation factor, wherein the impact parameter is used to characterize the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor; Based on the influencing parameter, the initial weight of the evaluation factor associated with the evaluation factor is adjusted.

8. The method according to claim 5, It is characterized in that The obtaining of evaluation parameters corresponding to each of the plurality of preset dimensions based on the adjusted initial weights corresponding to each of the plurality of evaluation factors in the plurality of rounds of adjustments includes: Based on the influence parameters between the evaluation factors having the association relationship, constructing a cross-influence probability matrix; The cross-impact probability matrix and the multiple evaluation factors correspond to each other in multiple rounds of adjustment The adjusted initial weights are iterated multiple times until the preset end condition is reached; Based on the cross-influence probability matrix when the preset end condition is reached, the evaluation parameters corresponding to each of the plurality of preset dimensions are obtained.

9. The method according to claim 1, It is characterized in that The step of determining the grading parameter of the entity area for the target business based on the plurality of evaluation parameters and the plurality of dimension information includes: Quantizing the multiple dimensional information to obtain a quantized value corresponding to each dimensional information; Based on the multiple evaluation parameters and the multiple quantitative values, determining the quantitative scoring values ​​corresponding to the multiple evaluation factors; Based on each of the quantitative score values, the ranking parameters are determined.

10. The method according to claim 9, It is characterized in that After determining the quantitative scoring values ​​corresponding to the plurality of evaluation factors based on the plurality of evaluation parameters and the plurality of quantitative values, the method further comprises: Determining a difference between the evaluation parameter and the corresponding quantitative score value; Based on the difference, determining at least one target evaluation factor from the plurality of evaluation factors; Output the recommendation information corresponding to each of the target evaluation factors.

11. The method according to claim 9, It is characterized in that The plurality of business information comes from a plurality of information collection devices, and the method further comprises: In the case where the grading parameter is lower than a preset grading parameter, determining a target preset dimension where the difference between the quantitative score value and the evaluation parameter is greater than a preset difference; Control the target information collection device to output warning information; wherein, the target information collection device is used to collect business information of the target preset dimension.

12. The method according to claim 1, It is characterized in that The method further comprises: Obtaining the classification parameters corresponding to the entity area in a plurality of different time periods; Based on the corresponding grading parameters in the multiple different time periods, the grading statistical information of the physical area is output to indicate the grading changes of the physical area in the target business in different time periods.

13. The method according to claim 1, It is characterized in that The obtaining of multiple business information of the entity area in the target business includes: When the preset time period arrives, in response to the classification target of the preset time period, the entity area is obtained. The domain includes service information corresponding to the classification target in the target service; wherein the classification targets corresponding to different preset time periods are the same or different; Among them, a plurality of the preset dimensions correspond to the grading targets.

14. The method according to claim 1, It is characterized in that The acquiring of multiple business information of the entity area in the target business includes: Sending information collection instructions to a plurality of information collection devices located in the physical area to instruct the information collection devices to collect facility status of the configured facilities; Acquire the business information collected by the multiple information collection devices after performing the information collection.

15. An information processing system, It is characterized in that It includes an Internet of Things platform and a plurality of information collection devices connected to the Internet of Things platform; wherein: The multiple information collection devices are used to collect business information of the entity area on the target business; The Internet of Things platform is used to execute the information processing method described in any one of claims 1-14.

16. An evaluation parameter output device, It is characterized in that The device comprises: A factor acquisition module, used to acquire a plurality of evaluation factors corresponding to the target business in the entity area from a database corresponding to the target business; wherein one evaluation factor corresponds to a preset dimension of the target business; A parameter determination module, used to determine the evaluation parameters corresponding to the various evaluation factors; An output module is used to send the evaluation parameters to an information processing platform, so that the information processing platform determines the grading parameters of the entity area on the target business based on a plurality of the evaluation parameters and a plurality of dimensional information; wherein the grading parameters are used to indicate the level to which the entity area belongs; wherein the information processing platform is an Internet of Things platform, or the information processing platform and the evaluation parameter output device are integrated into the Internet of Things platform; The dimension information is obtained by clustering multiple businesses according to multiple preset dimensions, and the multiple business information at least includes status information of different facilities in the physical area.

17. The evaluation parameter output device according to claim 16, It is characterized in that The parameter determination module comprises: A relationship building unit, used to build a correlation relationship between a plurality of the evaluation factors; A weight acquisition unit is used to output the association relationship and receive the input for each evaluation factor. The initial weight of input; A parameter determination unit is used to determine the evaluation parameters corresponding to each of the preset dimensions based on the initial weights.

18. The evaluation parameter output device according to claim 17, It is characterized in that The device also includes: an influencing parameter determination module and an adjustment module; The impact parameter determination module is used to receive the impact parameters input for the evaluation factors with associated relationships, and the impact parameters are used to represent the degree of influence of the occurrence of an event represented by one evaluation factor on the occurrence of an event represented by another evaluation factor; The adjustment module is used to adjust the initial weight of each of the evaluation factors based on the influencing parameters; The parameter determination unit is specifically used to determine the evaluation parameters corresponding to each of the preset dimensions based on the adjusted initial weights.

19. The evaluation parameter output device according to claim 18, It is characterized in that The device also includes: an iterative adjustment module; The iterative adjustment module is used to adjust the initial weights of multiple evaluation factors in sequence, wherein, when each evaluation factor is adjusted, the initial weights of the evaluation factors associated with the evaluation factor are adjusted based on the random number corresponding to the evaluation factor; Wherein, when adjusting the initial weight of the evaluation factor associated with the evaluation factor, the initial weight of the evaluation factor is adjusted using the influencing parameter determination module and the adjustment module; The parameter determination unit is specifically used to obtain the evaluation parameters corresponding to each of the multiple preset dimensions based on the adjusted initial weights corresponding to each of the multiple evaluation factors in multiple rounds of adjustments.

20. A computer-readable storage medium, It is characterized in that The computer program stored therein enables the processor to execute the information processing method as described in any one of claims 1 to 14.

Images