77 results about "Early warning score" patented technology

The invention relates to a bridge safety early warning method and system based on construction monitoring, and belongs to the technical field of bridge engineering.The early warning method comprises the steps that multi-dimensional monitoring data collected by sensor networks deployed on a bridge girder and a bridge key section in real time are obtained; performing edge calculation processing on the multi-dimensional monitoring data to obtain a cleaned monitoring data set; based on the cleaned monitoring data set, combining a finite element model to construct a three-dimensional dynamic stress field, and generating a dynamic stress nephogram matrix; dynamically correcting a pre-configured stress allowable threshold value according to the environment monitoring data; predicting a stress prediction matrix in a future time window based on historical stress data and the dynamic stress nephogram matrix; the real-time stress value and the stress prediction matrix are compared with a preset stress allowable threshold value, and an early warning score is calculated; and determining a corresponding early warning level according to the early warning score and triggering a maintenance control strategy. According to the invention, the accuracy of bridge structure risk early warning can be improved.

The invention provides an insurance customer fraud detection method and system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the steps: building a nonlinear mapping relation between a feature variable and a target variable, calculating a partial correlation coefficient between features, recognizing a causal relation, and generating an insurance fraud field causal atlas; identifying a trigger factor based on a time sequence intervention effect and an anti-fact effect; calculating a transfer coefficient and loop strength of the causal path to obtain a link credibility score; and fusing the trigger factor and the link credibility score to generate an early warning score, and extracting a maximum cumulative transfer effect path to output an early warning result. According to the method, the insurance fraud behavior can be accurately identified, and the accuracy and interpretability of fraud detection are improved.

The invention relates to the technical field of construction site safety early warning, in particular to a multi-modal construction site safety early warning method and system for dynamic weight allocation, and the method comprises the following steps: deploying a multi-modal data collection module, and collecting and transmitting construction site data to a central processing unit in real time; constructing a correlation model according to the historical accident database; carrying out preprocessing and anomaly detection on real-time data, and dynamically adjusting a multi-modal weight according to a result; inputting the adjusted weight into the model, calculating a comprehensive early warning score and performing graded early warning; and correcting the model according to the early warning and accident matching degree. According to the method, the multi-modal data acquisition module is deployed to acquire sensor, visual and text data, and a dynamic weight distribution mechanism is combined, so that the weight of each modal can be adjusted in real time according to an anomaly detection result, the accuracy and comprehensiveness of potential safety hazard identification are remarkably improved, and the problems of one-sidedness and missing report of single-modal monitoring are effectively avoided.

The invention belongs to the technical field of river and lake water quality monitoring, and discloses a river and lake water quality intelligent traceability monitoring system and method.Dissolved organic matter fluorescent fingerprints are analyzed in real time through a three-dimensional fluorescent monitoring unit, pollution markers are detected, and parameters such as COD, ammonia nitrogen and total phosphorus are synchronously detected through a full-spectrum monitoring unit; the video monitoring unit is used for collecting section images / videos of rivers and lakes, other sensors are used for collecting real-time values of chlorophyll, pH, conductivity, turbidity and dissolved oxygen in a water body, then the data processing module is used for carrying out normalization processing on multi-source data, and the analysis and early warning module is used for analyzing water quality early warning scores, spectrum early warning scores and video early warning scores. All scores are synthesized to obtain a comprehensive early warning score, traceability is started when comprehensive early warning is larger than or equal to the grade II, pollution sources are recognized based on three-dimensional fluorescence spectrum comparison and upstream patrol, and a river and lake water body monitoring-early warning-traceability-verification closed loop is achieved.

The invention discloses a supply chain performance path optimization and collaborative decision-making method based on an AI algorithm, and particularly relates to the field of supply chain performance path optimization, and the method comprises the steps: firstly obtaining order goods information and warehouse resource data, and judging whether a single warehouse can independently perform a performance or not through matching; if yes, constructing a comprehensive evaluation function including total transportation time, time redundancy, path complexity and resource utilization rate, and generating an optimal path from the warehouse to the delivery place; if multi-warehouse collaboration is needed, dynamically selecting a centralized point warehouse, generating a comprehensive early warning score and selecting an optimal centralized point by comprehensively calculating the cargo transfer cost and the historical performance risk value of each warehouse, and finally planning a transfer path from a supply warehouse to the centralized point and a performance path from the centralized point to a terminal to form a full-link collaboration scheme; according to the method, a traditional single-warehouse decision mode is broken through, global resource scheduling is realized through a double-path optimization mechanism, the transportation delay risk is remarkably reduced, and the supply chain operation efficiency is improved.

The invention relates to the technical field of processing supervision, and discloses a supervision early warning system and method for tobacco leaf baking processing, the system comprises a monitoring module and an early warning part, and the early warning part comprises an acquisition module, an evaluation module, a central control module and an early warning module. According to the invention, the monitoring module is responsible for monitoring the ventilation quantity and the ventilation temperature of each monitoring area in real time and transmitting the data to the acquisition module; the acquisition module obtains a data difference value in combination with historical data, the central control module is used for screening data, data exception is identified through a Gaussian mixture model, and then an exception monitoring area is determined. The evaluation module calculates an early warning score according to the baking data of the abnormal area, and finally the early warning module judges whether early warning information is triggered or not. According to the anomaly detection method based on data difference analysis and the Gaussian mixture model, potential risks can be effectively identified, and the stability and safety of the baking process are ensured.

The invention provides an electric power operation ground wire intelligent positioning and early warning control method and system, and relates to the technical field of electric power operation safety monitoring, and the method comprises the steps: constructing a double-layer architecture cooperative intelligent positioning system, processing multi-source sensing data through employing a self-adaptive particle swarm optimization data fusion algorithm, and optimizing a spatial topological relation through a graph attention mechanism; extracting features from the time sequence state sequence by adopting multi-scale and cavity convolution, and constructing a space-time double-flow heterogeneous graph; and in combination with a power operation field knowledge graph and Monte Carlo tree search, risk early warning scoring is realized. According to the invention, the grounding wire position monitoring precision and the risk early warning accuracy are improved, and the power operation safety guarantee capability is enhanced.

The invention relates to the technical field of medical information, in particular to an osteoporosis risk intelligent early warning method and system based on a big database. The method comprises the following steps: extracting user bone health data in a multi-source health database; evaluating a bone mass state based on the user bone health data; screening osteoporosis risk users in the user bone health data according to the bone mass state; inquiring a medical image of the osteoporosis risk user; extracting a bone mineral density value by using the medical image, and determining a bone mineral density change trend according to the bone mineral density value; detecting the degeneration degree of the bone microstructure by using a medical image; constructing an osteoporosis risk early warning model according to the bone mineral density change trend and the bone microstructure degeneration degree; and inputting the user bone health data into the osteoporosis risk early warning model to generate a risk early warning score. According to the invention, accurate identification and dynamic monitoring of the osteoporosis risk user are realized based on the medical information technology, and the accuracy and response rate of osteoporosis risk early warning are improved.

The invention relates to the technical field of tobacco leaf monitoring, and discloses an intelligent monitoring method, medium and system for bubble-shaped green spots in cigar tobacco leaf air-curing, and the method comprises the steps: obtaining the image information of the bubble-shaped green spots in cigar tobacco leaf air-curing, and building a bubble-shaped green spot feature set according to the features of the image information; then, surface images of all cigar tobacco leaves in the airing area are obtained, and feature matching is carried out; and when the surface image features are matched with the bubble-shaped green spot features, determining that the tobacco leaves are sick tobacco leaves. And calculating an early warning score of the air-curing area based on the number of the patient tobacco leaves and the patient grade. Meanwhile, the illuminance of all the tobacco leaves and the environment temperature and humidity of the air-curing area are obtained so as to adjust the early warning score. And finally, according to the adjusted early warning score, determining the early warning grade of the airing area. Through combination of image analysis and environment monitoring, effective early warning and management of tobacco leaf diseases are realized.

The invention relates to the field of building fire defense, and provides an intelligent building monitoring management system based on the Internet of Things, and the system comprises a DS evidence theory module and a management module which are carried on an Internet of Things cloud platform. The DS evidence theory module generates a fire early warning score based on a first evidence set, a second evidence set or a third evidence set, the first evidence set is constructed based on collection values of multiple sensors in a set area, and the second evidence set is constructed based on the first evidence set and the area scene association degree of the multiple sensors and the set area; the third evidence set is constructed based on the correlation degree between the second evidence set and the multiple sensors; the management module carries out management, display and early warning on the plurality of fire early warning scores of the plurality of set areas. According to the invention, comprehensive fire early warning for different types of sensors in different areas in the building is realized through the DS evidence theory, and a more intelligent fire early warning function of the Internet of Things monitoring management system of the building is realized.

The invention discloses a pipeline corrosion bilateral early warning method based on dynamic weight fusion, and belongs to the technical field of oil and gas pipeline safety intelligent monitoring. According to the method, aiming at the problems of single-model evaluation dimension limitation and insufficient risk factor coupling analysis in the existing corrosion early warning technology, comprehensive early warning is realized by constructing a failure early warning and risk early warning dual-model cooperation mechanism. According to the technical scheme, the method comprises the steps of collecting multi-source corrosion monitoring data and classifying the multi-source corrosion monitoring data into a failure feature set and a risk feature set, establishing a corrosion failure early-warning model based on a residual strength criterion to output a failure early-warning score, adopting a DHGF algorithm to establish a corrosion risk early-warning model to output a risk early-warning score, utilizing an elk optimization algorithm to optimize a dynamic weight coefficient, and obtaining a corrosion risk early-warning result. And obtaining a comprehensive early warning score through weighted fusion. According to the method, the problem of misjudgment caused by single early warning dimension and weight solidification of a traditional method is solved, the accuracy and decision reliability of pipeline corrosion early warning are remarkably improved, and the method is suitable for intelligent safety monitoring of oil and gas pipelines.

The invention discloses an operation monitoring method and system for a heavy-load multi-stage centrifugal pump. The method comprises the steps that operation data of operation parameters of all stages in the multi-stage centrifugal pump are synchronously collected; performing deviation analysis on the operation data of each level of operation parameters by utilizing a nonlinear coupling model, extracting sensitive operation parameters which are remarkably deviated from normal coupling behaviors, and forming a sensitive operation parameter set; carrying out trend analysis and coupling mutation analysis on the sensitive operation parameters, and extracting disturbance operation parameters serving as disturbance sources from the sensitive operation parameter set in combination with a deviation analysis result to form a disturbance operation parameter set; and a self-adaptive dynamic threshold value of the disturbance operation parameters is generated, and a multi-factor fusion early warning scoring function is constructed to carry out potential operation fault monitoring and early warning on the multi-stage centrifugal pump. According to the method, by constructing a self-adaptive dynamic threshold value and multi-factor fusion scoring mechanism, the recognition capability of pump stage coupling state changes is enhanced, and intelligent grading early warning of fault symptoms is achieved.

The invention belongs to the technical field of risk early warning, and provides a customs risk early warning method and system based on cross-modal retrieval enhancement, and the method comprises the steps: obtaining a customs task instruction data set; performing cross-table retrieval on the acquired customs task instruction data set based on a hierarchical weighted table retrieval enhancement method to obtain a structured evidence packet of the data set; performing cross-modal understanding on the obtained structured evidence packet according to a multi-modal large model to obtain early warning middleware of the data set; and performing early warning scoring on the obtained early warning middleware to complete customs risk early warning based on cross-modal retrieval enhancement. The multi-modal large model is adopted, the space-channel decoupling attention gating module and the self-adaptive hierarchical feature selection module are adopted, the information fidelity is guaranteed, efficient fusion of multi-layer feature representation is achieved at the same time, feature representation with higher discriminative force is provided for multi-modal reasoning, and the multi-modal reasoning accuracy is improved. And the automatic identification and early warning level of prohibited goods and high-risk goods in the customs clearance process is improved.

The invention provides a pavement construction early warning method and device based on multi-dimensional data and electronic equipment, and relates to the technical field of intelligent monitoring, and the method comprises the steps: obtaining pavement vibration data, equipment inclination data and positioning environment data through ground nail equipment; inputting the road surface vibration data, the equipment inclination data and the positioning environment data into a data cleaning model, and performing false alarm filtering through the dynamic integral accumulation algorithm to obtain a construction early warning comprehensive score; and determining a construction early warning strategy based on the construction early warning comprehensive score. According to the invention, vibration monitoring, inclination angle sensing and geographical environment multi-dimensional data are fused, an intelligent construction early warning system is constructed, and the early warning accuracy is improved.

The invention discloses a ship positioning and intelligent early warning system based on a Beidou satellite, and belongs to the technical field of ship safety management, and the system specifically comprises the steps: obtaining ship data and wind power data of a target area; according to the ship data and the wind power data, determining a buffer area of any ship outside a target area, if any ship is located in the buffer area, calibrating the ship as an undetermined ship, and generating a shortest distance change curve from the ship to the target area in a monitoring period; feature points in the change curve are obtained, a change coefficient Q is calculated, an early warning score P is calculated according to the change coefficient and the change curve, if P is larger than P ', the undetermined ship is marked as an abnormal ship, and early warning information is sent to the abnormal ship. According to the invention, the accuracy of ship supervision is improved.

The present invention proposes a potential risk personnel early warning system based on XXL scheduled scheduling, which includes: a custom early warning module, a rule verification module, a scheduling module and a matching module, wherein the custom early warning module is used to configure an early warning template containing data source rules, scoring rules and proportions; the rule verification module is used to determine whether the template configured in the custom early warning module complies with the configuration rules. If it does not comply, the custom early warning module is re-entered to modify the early warning template; if it complies, the early warning template is submitted and an early warning task is initiated; the scheduling module receives the early warning task, schedules the execution of the early warning task through the XXL Job scheduler, presents the execution result on the front-end page, and directly optimizes the early warning template on the front-end page to obtain the optimized early warning model; the matching module is used to match the input data one by one with the early warning model, calculate the early warning score and obtain the early warning result.

The present invention provides a generation management method for an API, comprising: determining a target call state according to an activity balance and a call interval of active APIs, and determining a cache adjustment method according to the target call state to adjust the cache cleanup cycle, or to set a cache mechanism or adjust the cache scale; when setting the cache mechanism, detecting the sensitive information state and determining the cache mechanism to be a circular cache or a weighted cache according to the sensitive information state; when adjusting the cache scale, determining a warning score according to an operational characteristic risk factor of a target requester, and determining proportional adjustment or conventional adjustment for the cache scale according to a comparison result between the warning score and a preset warning score; in the proportional adjustment, determining whether to encrypt or hide the API front-end cache according to a comparison result between a hierarchical diversity value and a preset hierarchical diversity value. The present invention improves the efficiency of API generation management.

The application discloses a supply chain performance path optimization and collaborative decision-making method based on an AI algorithm, and particularly relates to the field of supply chain performance path optimization, and comprises the following steps: firstly, order goods information and warehouse resource data are acquired, and it is judged whether a single warehouse can independently perform the performance by matching; if yes, a comprehensive evaluation function containing total transportation time, time redundancy, path complexity and resource utilization rate is constructed, and an optimal path from the warehouse to a delivery place is generated; if multiple warehouses need to be cooperated, a centralized point warehouse is dynamically selected, the goods transfer cost and historical performance risk value of each warehouse are comprehensively calculated, a comprehensive early warning score is generated, and an optimal centralized point is selected, finally, the transfer path from the supply warehouse to the centralized point and the performance path from the centralized point to the terminal are planned, and a full-link collaborative scheme is formed; the application breaks through the traditional single-warehouse decision-making mode, realizes global scheduling of resources through a double-path optimization mechanism, significantly reduces the transportation delay risk, and improves the operation efficiency of the supply chain.

The invention discloses an asset health assessment method and system based on UWB-RFID tags, and belongs to the technical field of asset assessment, each asset corresponds to one UWB-RFID tag, and the assessment method comprises the steps: classifying assets in a region, carrying out the tag quality scoring and tag computing power calculation of the UWB-RFID tags of the assets in real time, and obtaining the risk early warning scores of the assets; performing initial health scoring on each asset by using the trained XGBoost model, and punishing the initial health scores based on asset abnormal movement identified in real time to obtain final health scores of the assets; and obtaining the health score of each type of assets and the asset health score of the whole area based on the final health score of each asset. According to the invention, the health conditions of all assets can be obtained in real time, and the refinement level of management and control and decision making is improved under the condition of ensuring that the health assessment result is objective, accurate and comprehensive.

The invention relates to the technical field of intelligent manufacturing, and discloses a logistics execution strategy determination method and device, electronic equipment and a storage medium, and the method comprises the steps: determining current storage data, current logistics data and current loading and unloading data from different types of system data in a current logistics supply chain; obtaining a plurality of simulation strategies according to the current storage data, the current logistics data and the current loading and unloading data; according to the simulation storage space utilization rate, the simulation logistics damage rate and the simulation loading and unloading safety value of each simulation strategy, an early warning score of each simulation strategy is obtained through calculation, and the simulation strategy with the minimum early warning score serves as an execution strategy. According to the invention, the logistics supply chain can be adjusted in real time foreseeably, so that the flexible management degree and the risk regulation and control degree of the logistics supply chain are improved.

The embodiment of the invention provides an emergency patient intelligent scoring method and system based on a special disease scoring tool. The method comprises the following steps: capturing pressure fluctuation characteristics and a microbial leakage threshold value of a biological sample of an emergency patient in a transmission process in real time, synchronously analyzing use conditions of an antiviral drug, an antibiotic and an immunomodulator, calculating a transmission risk value of the individualized biological sample, and constructing a dynamic transmission risk map. And by fusing the pressure fluctuation characteristics of the atlas and an immunomodulator administration mode, generating an early warning score grade, triggering a shunting instruction to isolate a high-risk sample, and adjusting the airflow parameter and the drug storage priority of a negative pressure isolation region. The method effectively improves the efficiency and safety of infectious disease patient management, and achieves the precise medical resource distribution and risk control. According to the technical scheme provided by the embodiment of the invention, the capability of coping with infectious disease emergencies of hospitals is remarkably improved.

The present application relates to the technical field of construction site safety early warning, in particular to a multi-modal construction site safety early warning method and system with dynamic weight distribution, comprising the following steps: deploying a multi-modal data acquisition module, collecting and transmitting construction site data to a central processing unit in real time; constructing a correlation model according to a historical accident database; pre-processing real-time data and detecting abnormalities, and dynamically adjusting the multi-modal weight according to the results; inputting the adjusted weight into the model, calculating the comprehensive early warning score and grading the early warning; correcting the model according to the early warning and accident matching degree. The present application collects three types of data, namely sensors, vision and text, by deploying a multi-modal data acquisition module, and combines a dynamic weight distribution mechanism, which can adjust the weight of each mode in real time according to the abnormal detection results, significantly improves the accuracy and comprehensiveness of safety hazard identification, and effectively avoids the one-sidedness and missed reporting problems of single-mode monitoring.

The invention relates to an unmanned vehicle control software evaluation method based on physiological signals, belongs to the technical field of software man-machine work efficiency evaluation, and solves the problem of low reliability of an unmanned vehicle control software evaluation mode in the prior art. The unmanned vehicle control software evaluation method comprises the following steps: collecting first physiological signals generated when a plurality of operators operate unmanned vehicle control software according to a standardized task process; constructing an early warning scoring baseline and a man-machine work efficiency scoring baseline of the unmanned vehicle control software according to the first physiological signals generated by the plurality of operators; acquiring a second physiological signal generated when a plurality of operators operate the unmanned vehicle control software according to the normal task process; second physiological signals generated by the multiple operators are counted, and whether the unmanned vehicle control software is qualified or not is determined based on the early warning scoring base line and the man-machine work efficiency scoring base line. The reliability of quantitative evaluation of the unmanned vehicle control software is higher.

The invention provides a risk detection method and a risk detection device for oil and gas pipeline network equipment. The method comprises the following steps: acquiring network interface flow data generated by a plurality of network equipment in a network environment of an oil and gas pipeline valve chamber; performing feature extraction on the network interface traffic data to obtain feature data including a plurality of feature dimensions; inputting the feature data into a pre-trained dual anomaly analysis model, determining abnormal risk traffic data, and determining a network device to which the risk traffic data belongs as a risk device; wherein the dual anomaly analysis module comprises a time sequence model and an early warning score model. Through the method and the device, the capability of detecting the abnormal flow data of the valve chamber side of the oil and gas pipeline is improved, and the efficiency and the accuracy of risk detection of the network equipment of the valve chamber side of the oil and gas pipeline are also improved.

The invention relates to the technical field of medical first aid, and discloses an early recognition method for emergency sepsis patients through combination of NEWS and CRT, and the method comprises the following steps: collecting physiological parameters of the patients during emergency treatment, the physiological parameters including respiratory rate, heart rate, systolic pressure, body temperature, oxyhemoglobin saturation and consciousness state; and calculating an early warning score NEWS of the British country according to the physiological parameters, and when the NEWS score is greater than 4.07, prompting that the patient has a sepsis risk. According to the method, the whole body circulation and microcirculation states of a patient can be evaluated at the same time through combined use of the NEWS and the CRT, so that the accuracy of early recognition of sepsis is improved, compared with a single-index evaluation method, the NEWS and the CRT are combined, the illness state of the patient can be reflected more comprehensively, misdiagnosis and missed diagnosis conditions are reduced, and the accuracy of early recognition of sepsis is improved. And especially in the early stage with hidden illness state.

The application discloses a short-term and impending roof fall early warning method for underground mines based on multi-source monitoring and partition early warning values, and comprises the following steps: S1, multi-source monitoring is conducted on roof fall to obtain multi-source monitoring data; S2, based on existing several stope falling rock mass influencing factors, specific influencing factors are screened, and partition early warning is conducted based on the specific influencing factors, and an early warning value early warning scoring system of rock mass internal fracture and surface deformation is established; and S3, the early warning value early warning scoring system of rock mass internal fracture and surface deformation is utilized to conduct actual partition early warning. The method is based on multi-source monitoring means, and meanwhile, the specific engineering geological condition partition of the monitoring object is considered, different early warning values are set for different partitions, and the short-term and impending early warning accuracy is remarkably improved.

The invention discloses an abnormity early warning platform and method based on energy data flow type calculation, and the method comprises the steps: obtaining an energy data flow, and carrying out the preprocessing of the energy data flow, and obtaining a standardized energy data flow; when the monitoring data greater than the corresponding early warning threshold exists in the standardized energy data flow and the corresponding duration is greater than the preset duration threshold, directly performing early warning reminding; otherwise, determining the first data stream through the standardized data stream; performing sub-window selection on the first data stream, and determining a sub-window of each piece of monitoring data; analyzing according to the sub-windows of the monitoring data, and determining one or more overlapping intervals; and for each fault type, respectively determining a total early warning score and a corresponding early warning level, and carrying out corresponding early warning reminding. Through real-time acquisition, intelligent preprocessing and multi-energy data comprehensive analysis of energy data, timeliness and accuracy of energy system abnormity monitoring are improved, and energy waste and operation and maintenance risks are reduced.

The application relates to the technical field of monitoring management, and discloses a monitoring management method and system for equipment working conditions, which comprises the following steps: determining the authority importance value of each equipment department according to department information and a department authority model, determining the management authority of each equipment department based on the authority importance value, comparing an equipment monitoring parameter set with a standard equipment monitoring parameter set, dividing each equipment monitoring parameter in the equipment monitoring parameter set according to a comparison result, constructing an equipment monitoring space according to the equipment position of the equipment, mining the association result of an environmental data set and an equipment parameter set according to an association rule algorithm, determining the adjustment coefficient of an initial early warning score based on the association result, comparing a target early warning score with data in a historical target early warning score database, and judging whether to give an early warning according to a comparison result. The application effectively reduces the monitoring difficulty and the workload, thereby guaranteeing the monitoring efficiency.

The invention provides an employee job number behavior early warning method and device and a readable storage medium, and the method comprises the steps: obtaining the query and acceptance order conditions of a target employee job number in a plurality of account periods, and the plurality of account periods comprise a current account period and at least one historical account period; obtaining an early warning index of the job number of the target employee in each account period according to the query and acceptance order condition of the job number of the target employee in each account period in the plurality of account periods; calculating a target early warning score of the target employee job number by using a preset early warning scoring rule according to the early warning index of the target employee job number in each account period; and judging whether the behavior of the target employee job number is abnormal or not according to the target early warning score of the target employee job number. According to the method, the device and the readable storage medium, the problem that an existing employee job number behavior early warning method is single in consideration factor, so that an early warning result is not accurate enough can be solved.

The application discloses a battery state evaluation method and device, electronic equipment and storage medium, comprising: when receiving a battery product evaluation request, obtaining fault handling data, early warning data, SOH analysis data and working condition analysis data of the battery product to be evaluated, and determining a fault score, an early warning score, an SOH score and a working condition score of the battery product; using the fault score, the early warning score, the SOH score and the working condition score to determine a comprehensive score of the battery product; and determining the battery state of the battery product according to the comprehensive score. The fault score, the early warning score, the SOH score and the working condition score reflect the battery state from different angles, and the four types of scores are used for comprehensive scoring, the battery state of the battery product is evaluated according to the final comprehensive score, the problem product can be fully identified, the battery state can be represented from all aspects and multiple levels, and it is beneficial to investigate the risk product and reduce the after-sales cost.