Disclosure of Invention
In view of the above, the invention provides an artificial intelligence-based loss assessment rule screening method, device, equipment and medium, which aim to solve the technical problems that in the prior art, the hit matching rate of rules is lower and the operation load of a CPU is higher.
In order to achieve the above object, the present invention provides a method for screening impairment rules based on artificial intelligence, the method comprising:
Reading a to-be-damaged item from a preset database, and matching the to-be-damaged item with a damage rule in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; wherein the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule;
scoring the triggered damage assessment rule based on a preset first calculation rule, and scoring the non-triggered damage assessment rule based on a preset second calculation rule to obtain scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule;
Feeding back the triggered loss assessment rules and the sorting results of the non-triggered loss assessment rules based on the grading values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set;
And executing union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, storing the target loss assessment rule set into the loss assessment rule engine, and feeding back all loss assessment rules of the target loss assessment rule set to a preset user.
Preferably, the matching the to-be-damaged item with a damage rule in a preset damage rule engine includes:
A1, reading any accessory in the items to be damaged and matching the accessory with the damage rule in the damage rule engine, and obtaining a damage assessment result of the accessory when the attribute information of the accessory is successfully matched with all sub-rules in the damage assessment rule;
a2, when the attribute information of the accessory is failed to be matched with any one of the sub-rules in the damage assessment rule, the prompt information is fed back to a preset user according to the sub-rule with failed matching, the modification information sent by the preset user according to the prompt information is received, and when the modification information is successfully matched with the sub-rule in the damage assessment rule, the damage assessment result of the accessory is obtained.
A3, repeating the steps A1-A2 until each accessory in the item to be damaged is matched with the damage assessment rule in the damage assessment rule engine to obtain a damage assessment result.
Preferably, the obtaining the triggered damage assessment rule set and the non-triggered damage assessment rule set of the to-be-determined damage item includes:
when any accessory in the items to be damaged is successfully matched with the damage assessment rules in the damage assessment rule engine, reading the damage assessment rule of the damage assessment result successfully matched from the damage assessment rule engine as the triggered damage assessment rule set;
when any accessory in the items to be damaged is failed to be matched with the damage rule in the damage rule engine, the damage rule which is failed to be matched is read from the damage rule engine as the non-triggered damage rule set.
Preferably, the formula of the first calculation rule includes:
Wherein, Pi is the scoring value of the ith triggered loss rule, Xi is the detected task number of the ith triggered loss rule, Yi is the task number of the ith triggered loss rule, and a is the score coefficient.
Preferably, the formula of the second calculation rule includes:
Ni＝(T1-T2)×W×a
Ni is the scoring value of the ith non-triggered damage rule, T1 is the creation time point of the ith non-triggered damage rule, T2 is the current time point, W is the rule weight, and a is the scoring coefficient.
Preferably, the receiving feedback information sent by the first user based on the sorting result includes:
And sorting the triggered damage assessment rule and the non-triggered damage assessment rule from high to low based on the grading value to obtain a sorting result, and taking information selected by the first user from the sorting result as the feedback information.
Preferably, the feeding back all the impairment rules of the target impairment rule set to a preset user includes:
Reading the weight value of each loss rule in the target loss rule set in the loss rule engine, and multiplying the weight value by a preset coefficient to obtain a target weight value;
And sequencing each loss assessment rule in the target loss assessment rule set from high to low according to the target weight value, and setting the feedback times and time periods of each loss assessment rule fed back to the preset user according to the sequencing result.
In order to achieve the above object, the present invention further provides a loss assessment rule screening apparatus, the apparatus comprising:
The acquisition module is used for: the method comprises the steps of reading a to-be-damaged item from a preset database, and matching the to-be-damaged item with damage rules in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; wherein the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule;
The calculation module: the method comprises the steps of scoring the triggered damage assessment rule based on a preset first calculation rule, scoring the non-triggered damage assessment rule based on a preset second calculation rule, and obtaining scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule;
And (3) selecting a module: the method comprises the steps of feeding back the triggered loss assessment rules and the non-triggered loss assessment rules to a first user based on a sorting result of the grading values, receiving feedback information sent by the first user based on the sorting result, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set;
And a recommendation module: and the method is used for executing union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, storing the target loss assessment rule set into the loss assessment rule engine, and feeding back all loss assessment rules of the target loss assessment rule set to a preset user.
To achieve the above object, the present invention also provides an electronic device including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a program executable by the at least one processor to enable the at least one processor to perform the artificial intelligence based impairment rules screening method according to any one of claims 1 to 7.
To achieve the above object, the present invention also provides a computer readable medium storing a damage rule screening program which, when executed by a processor, implements the steps of the artificial intelligence based damage rule screening method according to any one of claims 1 to 7.
The method comprises the steps of obtaining triggered damage assessment rules and non-triggered damage assessment rules from a damage assessment rule engine, scoring the triggered damage assessment rules and the non-triggered damage assessment rules to obtain scoring values, feeding back the sorting results of the triggered damage assessment rules and the non-triggered damage assessment rules based on the scoring values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a preset number of triggered damage assessment rules and non-triggered damage assessment rules as target damage assessment rule sets according to the feedback information, storing the target damage assessment rule sets into the damage assessment rule engine, and feeding back each damage assessment rule in the target damage assessment rule sets to the preset user. The invention can screen out the damage assessment rule with practicability and effectiveness, and feed back the damage assessment rule with practicability and effectiveness to all preset users, thereby improving the hit matching rate of the rule and reducing the operation load of the CPU.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The invention provides an artificial intelligence-based loss assessment rule screening method. Referring to fig. 1, a method flow diagram of an embodiment of an artificial intelligence based impairment rule screening method according to the present invention is shown. The method may be performed by an electronic device, which may be implemented in software and/or hardware. The loss rule screening method based on artificial intelligence comprises the following steps:
step S10: reading a to-be-damaged item from a preset database, and matching the to-be-damaged item with a damage rule in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule.
In this embodiment, the preset database may refer to a database built in the enterprise (for example, an insurance damage database of an insurance company). And taking staff for performing the loss assessment task, the quotation task and the instruction task in each business scene as preset users. The data of the damage assessment task, the quotation task and the instruction task, which are input into a preset database by a preset user (staff), are used as items to be subjected to damage assessment, (for example, the input data comprise vehicle basic information, repair shop information, accessory information, money information and the like).
The enterprise accumulates a large number of damage assessment rules (for example, damage assessment rules of the same automobile which are configured on the service differently, damage assessment rules of different suppliers of the same type of accessories which are provided with different prices, etc.) in each business scene in the past, and the preset damage assessment rule engine can apply a rule computing system according to the apache jexl expression language engine frame, and store the damage assessment rules accumulated by the enterprise into the preset damage assessment rule engine. When the accessory in the item to be evaluated is successfully matched with the evaluation rule in the evaluation rule engine, an evaluation result of the accessory is obtained and fed back to a preset user, the preset user makes an evaluation report according to the evaluation result and sends the evaluation report to a first user of an enterprise, and a worker in the enterprise with tasks of allocation, management of the preset user and approval authority on the evaluation report is used as the first user.
In one embodiment, the matching the to-be-damaged item with a damage rule in a preset damage rule engine includes:
A1, reading any accessory in the items to be damaged and matching the accessory with the damage rule in the damage rule engine, and obtaining a damage assessment result of the accessory when the attribute information of the accessory is successfully matched with all sub-rules in the damage assessment rule;
a2, when the attribute information of the accessory is failed to be matched with any one of the sub-rules in the damage assessment rule, the prompt information is fed back to a preset user according to the sub-rule with failed matching, the modification information sent by the preset user according to the prompt information is received, and when the modification information is successfully matched with the sub-rule in the damage assessment rule, the damage assessment result of the accessory is obtained.
A3, repeating the steps A1-A2 until each accessory in the item to be damaged is matched with the damage assessment rule in the damage assessment rule engine to obtain a damage assessment result.
The attribute information of the accessory comprises the name, the model, the parameters, the price, the model, the grade, the installation cost and the like of the accessory, for example, when each attribute information of the accessory A is successfully matched with all the sub-rules in the damage assessment rule E, the damage assessment result of the accessory A is obtained, all the sub-rules in the damage assessment rule E are in one-to-one correspondence with the attribute information of the accessory A, and each sub-rule comprises a plurality of sub-rules such as the accessory name, the model, the parameters, the price, the model, the grade, the installation cost of the corresponding vehicle, and the like, and only when each attribute information of the accessory A is successfully matched with each sub-rule in the damage assessment rule E, the damage assessment result of the accessory A can be obtained.
If a certain sub-rule in the damage rule E fails to match with certain attribute information of the accessory a, for example, the damage rule E is a damage rule of the accessory a, and other attribute information is successfully matched with the corresponding sub-rule except that the price (attribute information) fails to match with the price sub-rule, if the price in the accessory a is 400 yuan, the price of the sub-rule in the damage rule E is 350 yuan, and since the price of the accessory a is higher than the price of the damage rule E, the price lattice rule of the damage rule E fails to match with the price attribute information of the accessory a, the damage rule engine feeds back prompt information (for example, you are good, the price of the accessory a is submitted to a non-conforming condition, please modify) to a preset user, and the price of the accessory a is submitted to the damage rule engine again according to the prompt information to match until the price of the accessory a and the price sub-rule in the damage rule E are successfully matched, so as to obtain a damage result of the accessory a. In addition, after the preset user modifies the price of the accessory A for many times, when the matching of the price sub-rule in the damage assessment rule E fails, the accessory A can be selected to be matched with other rules, and the matching of the accessory A and the damage assessment rule E is abandoned. In an actual business scenario, each item to be damaged may involve multiple accessories to be damaged and claims to be damaged, and sometimes one accessory may match more than one damage rule successfully or multiple accessories may match one damage rule successfully at the same time.
In one embodiment, the obtaining the triggered impairment rule set and the non-triggered impairment rule set for the to-be-impaired item includes:
when any accessory in the items to be damaged is successfully matched with the damage assessment rules in the damage assessment rule engine, reading the damage assessment rule of the damage assessment result successfully matched from the damage assessment rule engine as the triggered damage assessment rule set;
when any accessory in the items to be damaged is failed to be matched with the damage rule in the damage rule engine, the damage rule which is failed to be matched is read from the damage rule engine as the non-triggered damage rule set.
Judging whether the damage item to be damaged is successfully matched with the damage assessment rule in the damage assessment rule engine, and when judging that each piece of attribute information of any accessory in the damage item to be damaged is successfully matched with each sub-rule in the damage assessment rule engine to obtain a damage assessment result, judging that the rule is a triggered damage assessment rule of the damage item to be damaged; when judging that the attribute information of any accessory in the items to be damaged is failed to be matched with any sub-rule in the damage rule engine, the rule is the non-triggered damage rule of the items to be damaged.
According to the prompting information of failure in matching sub rules in the damage rule in the accessory and damage rule engine, the preset user is guided to continuously modify attribute information of the accessory, and leakage risk of claim settlement is effectively reduced.
Step S20: the method comprises the steps of scoring the triggered damage assessment rule based on a preset first calculation rule, scoring the non-triggered damage assessment rule based on a preset second calculation rule, and obtaining scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule;
In this embodiment, the detection rate of the triggered damage rule is counted from the damage assessment rule engine, and the first calculation rule scoring is performed on the triggered damage assessment rule by multiplying the detection rate by the score coefficient, so as to obtain the scoring value of the triggered damage assessment rule. If two accessories A, B are simultaneously input, after all damage assessment rules are matched, a corresponding damage assessment rule E of the accessory A is obtained, a corresponding damage assessment rule F, G of the accessory B is obtained, in the matching process of each attribute information of the accessory, the accessory B is prompted to be not in accordance with the damage assessment rule G and cannot be matched to obtain a damage assessment result, after the attribute information of the accessory B is modified for many times, the damage assessment result is not obtained, the accessory B is removed, and only the damage assessment result of the accessory A is left to be in accordance with the damage assessment operation, and the accessory B is considered to have a one-time detection rate (detection task) on the damage assessment rule F, G. The score coefficient refers to the interval coefficient of the corresponding calculation rule, and is used for converting the detection rate (for example, a score interval of 0-100 is defined, if the corresponding detection rate range is 0-80, the score coefficient is 80 divided by 100 and is equal to 0.8).
Counting the creation time length of the non-triggered loss assessment rule from the loss assessment rule engine, and multiplying the creation time length by the score coefficient and the loss assessment rule weight in the loss assessment rule engine respectively to carry out second calculation rule scoring to obtain the score value of the non-triggered loss assessment rule. The time period from the creation time point of the damage rule to the current time point is read, and the time period is taken as the creation time length of the damage rule (for example, the creation time point of the damage rule G is 2021, 8, 1, 10, 00, and the current time is 2021, 8, 11, 10, 00, and the creation time length of the damage rule G is 10 days). Rule weights are priorities for defining each lossy rule according to the importance of the rule (e.g., priorities from high to low are a-F, their corresponding rule weight values range from 10-1).
In one embodiment, the formula of the first calculation rule includes:
Wherein, Pi is the scoring value of the ith triggered loss rule, Xi is the detected task number of the ith triggered loss rule, Yi is the task number of the ith triggered loss rule, and a is the score coefficient.
The task number refers to the number of damage assessment tasks, quotation tasks and guidance tasks of a preset user in the operation. And counting the detection rate of the triggered damage assessment rule, wherein the higher the detection rate is, the higher the effectiveness of the triggered damage assessment rule is, and the important effect is played on risk control such as fraud, seepage and the like in the damage assessment claim process.
For example, in a preset time period (for example, within 7 days), the number of detected tasks of the damage assessment rule E is 10, the number of tasks triggered by the damage assessment rule is 100, the score coefficient is 0.8, and data is input into the first calculation rule to obtain a score value of 0.08 of the damage assessment rule E.
In one embodiment, the formula of the second calculation rule includes:
Ni＝(T1-T2)×W×a
Ni is the scoring value of the ith non-triggered damage rule, T1 is the creation time point of the ith non-triggered damage rule, T2 is the current time point, W is the rule weight, and a is the scoring coefficient.
The higher the scoring value obtained by the non-triggered damage assessment rule, the worse the damage assessment effect of the non-triggered damage assessment rule, in addition, the creation time of the non-triggered damage assessment rule exceeds a preset value (for example, the preset value is 180 days), the damage assessment result is successfully obtained from the fact that the non-triggered damage assessment rule is not matched with any damage assessment item, the non-triggered damage assessment rule is automatically cleared from a preset damage assessment rule engine, a large number of non-business requirements or invalid damage assessment rules are prevented from occupying the storage space of the damage assessment rule engine, and the operation load of a CPU is reduced.
For example, the creation time point of the loss rule G is 2021, 8, 1, 10:00am, the current time is 2021, 8, 11, 10:00am, the corresponding rule weight value is 2, the score coefficient is 0.8, and the data is input into the second calculation rule to obtain the score value of the loss rule G as-16.
Step S30: feeding back the triggered loss assessment rules and the sorting results of the non-triggered loss assessment rules based on the grading values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set;
In this embodiment, the first calculation rule performs scoring to obtain that the scoring value of the triggered damage-assessment rule is positive, the second calculation rule performs scoring to obtain that the scoring value of the non-triggered damage-assessment rule is negative, the ranking result of the scoring value is fed back to the first user, when the first user receives the ranking result, the first user selects some damage-assessment rules with high scores or high detection rates from the positive ranking result on the operation interface as a first candidate rule set, and selects some damage-assessment rules with shorter creation duration and larger weight value from the negative ranking result as a second candidate rule set based on the working experience of the first user or the requirement of business development.
In one embodiment, the receiving feedback information sent by the first user based on the ranking result includes:
And sorting the triggered damage assessment rule and the non-triggered damage assessment rule from high to low based on the grading value to obtain a sorting result, and taking information selected by the first user from the sorting result as the feedback information.
The selected information refers to that the first user selects which rules according to the own working experience or the service development requirement, a first preset number of loss assessment rules with high grading values (for example, the first preset number may be 5000) are selected from the triggered loss assessment rules according to the sorting result, the first candidate rule set is used as a first candidate rule set, a second preset number of loss assessment rules with low grading values (for example, the second preset number may be 1000) are selected from the non-triggered loss assessment rules according to the sorting result, the number ratio of the triggered loss assessment rules to the non-triggered loss assessment rules is generally kept to be 10:2 or 10:1 as a second candidate rule set, if the ratio of the non-triggered loss assessment rules is too large, the influence on the implementation effect of the loss assessment rules is large, and meanwhile, some non-triggered loss assessment rules with short creation time or large weight values have enough opportunities to match the loss assessment items to obtain the loss assessment results.
Step S40: and executing union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, storing the target loss assessment rule set into the loss assessment rule engine, and feeding back all loss assessment rules of the target loss assessment rule set to a preset user.
In this embodiment, all the impairment rules in the first candidate rule set and the second candidate rule set are combined to obtain the target impairment rule set (for example, the first candidate rule set has 5000 rules, the second candidate rule has 1000 rules, the two rules are combined and added to obtain 6000 rules, the 6000 rules are taken as the target impairment rule set), the weight value of all the impairment rules in the target impairment rule set in the impairment rule engine is multiplied by a preset coefficient (for example, the preset coefficient is 1.2 or 1.5 times), all the impairment rules in the target impairment rule set are fed back to the preset user by using a feedback mechanism in the impairment rule engine, and the feedback mechanism is to give more feedback times to the impairment rules according to the greater weight value of the impairment rules, and the display period. The feedback mechanism feeds any one loss rule in the target loss rule set back to the operation interface of the preset user, so that the preset user can directly click the loss rule to match the items to be subjected to loss determination in an actual service scene, the preset user can conveniently and quickly find the high-efficiency loss rule, the preset user can be helped to save service time, and the working efficiency of the preset user is improved.
In one embodiment, the feeding back all impairment rules of the target impairment rule set to a preset user comprises:
Reading the weight value of each loss rule in the target loss rule set in the loss rule engine, and multiplying the weight value by a preset coefficient to obtain a target weight value;
And sequencing each loss assessment rule in the target loss assessment rule set from high to low according to the target weight value, and setting the feedback times and time periods of each loss assessment rule fed back to the preset user according to the sequencing result.
The specific weight value is multiplied by a preset coefficient to operate according to an actual service scene (for example, the weight value of each loss rule in the target loss rule set is multiplied by a coefficient of 1.2 or 1.5 times to obtain a target weight value, so that more feedback times and better display time periods are obtained in a feedback mechanism), for example, in a preset time period (within 7 days), the target weight value of the loss rule E in the target loss rule set is 8, the corresponding feedback times are 30 times, and the feedback time period is 10:00-12:00am and 14:00-16:00PM, wherein the target weight value of the loss assessment rule G in the target loss assessment rule set is 3, the corresponding feedback times are 10, and the feedback time period is 14:00-16:00PM, and each loss rule in the target loss rule set is given different presentation opportunities according to a feedback mechanism.
Referring to fig. 2, a functional block diagram of a loss rule screening apparatus 100 according to the present invention is shown.
The damage rule screening apparatus 100 of the present invention may be installed in an electronic device. According to the implemented functions, the impairment rule screening apparatus 100 may include an obtaining module 110, a calculating module 120, a selecting module 130, and a recommending module 140. The module of the present invention may also be referred to as a unit, meaning a series of computer program segments capable of being executed by the processor of the electronic device and of performing fixed functions, stored in the memory of the electronic device.
The functions of the respective modules/units are as follows in this embodiment:
The obtaining module 110 is configured to read a to-be-damaged item from a preset database, and match the to-be-damaged item with a damage rule in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule.
And the calculating module 120 is configured to score the triggered damage assessment rule based on a preset first calculating rule, score the non-triggered damage assessment rule based on a preset second calculating rule, and obtain the scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule.
Selection module 130: and the method is used for feeding back the sorting results of the triggered loss assessment rules and the non-triggered loss assessment rules based on the grading values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set.
And the recommendation module 140 is configured to perform a union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, store the target loss assessment rule set in the loss assessment rule engine, and feed back all loss assessment rules of the target loss assessment rule set to a preset user.
In one embodiment, the matching the to-be-damaged item with a damage rule in a preset damage rule engine includes:
A1, reading any accessory in the items to be damaged and matching the accessory with the damage rule in the damage rule engine, and obtaining a damage assessment result of the accessory when the attribute information of the accessory is successfully matched with all sub-rules in the damage assessment rule;
a2, when the attribute information of the accessory is failed to be matched with any one of the sub-rules in the damage assessment rule, the prompt information is fed back to a preset user according to the sub-rule with failed matching, the modification information sent by the preset user according to the prompt information is received, and when the modification information is successfully matched with the sub-rule in the damage assessment rule, the damage assessment result of the accessory is obtained.
A3, repeating the steps A1-A2 until each accessory in the item to be damaged is matched with the damage assessment rule in the damage assessment rule engine to obtain a damage assessment result.
In one embodiment, the obtaining the triggered impairment rule set and the non-triggered impairment rule set for the to-be-impaired item includes:
when any accessory in the items to be damaged is successfully matched with the damage assessment rules in the damage assessment rule engine, reading the damage assessment rule of the damage assessment result successfully matched from the damage assessment rule engine as the triggered damage assessment rule set;
when any accessory in the items to be damaged is failed to be matched with the damage rule in the damage rule engine, the damage rule which is failed to be matched is read from the damage rule engine as the non-triggered damage rule set.
In one embodiment, the formula of the first calculation rule includes:
Wherein, Pi is the scoring value of the ith triggered loss rule, Xi is the detected task number of the ith triggered loss rule, Yi is the task number of the ith triggered loss rule, and a is the score coefficient.
In one embodiment, the formula of the second calculation rule includes:
Ni＝(T1-T2)×W×a
Ni is the scoring value of the ith non-triggered damage rule, T1 is the creation time point of the ith non-triggered damage rule, T2 is the current time point, W is the rule weight, and a is the scoring coefficient.
In one embodiment, the receiving feedback information sent by the first user based on the ranking result includes:
And sorting the triggered damage assessment rule and the non-triggered damage assessment rule from high to low based on the grading value to obtain a sorting result, and taking information selected by the first user from the sorting result as the feedback information.
In one embodiment, the feeding back all impairment rules of the target impairment rule set to a preset user comprises:
Reading the weight value of each loss rule in the target loss rule set in the loss rule engine, and multiplying the weight value by a preset coefficient to obtain a target weight value;
And sequencing each loss assessment rule in the target loss assessment rule set from high to low according to the target weight value, and setting the feedback times and time periods of each loss assessment rule fed back to the preset user according to the sequencing result.
Referring to fig. 3, a schematic diagram of a preferred embodiment of an electronic device 1 according to the present invention is shown.
The electronic device 1 includes, but is not limited to: memory 11, processor 12, display 13, and network interface 14. The electronic device 1 is connected to a network through a network interface 14 to obtain the original data. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or a call network.
The memory 11 includes at least one type of readable medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 11 may be an internal storage unit of the electronic device 1, such as a hard disk or a memory of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are equipped with the electronic device 1. Of course, the memory 11 may also comprise both an internal memory unit of the electronic device 1 and an external memory device. In this embodiment, the memory 11 is generally used to store an operating system and various application software installed in the electronic device 1, such as program codes of the rule screening program 10. Further, the memory 11 may be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used for controlling the overall operation of the electronic device 1, e.g. performing data interaction or communication related control and processing, etc. In this embodiment, the processor 12 is configured to execute the program code stored in the memory 11 or process data, such as the program code of the rule screening program 10.
The display 13 may be referred to as a display screen or a display unit. The display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch device, or the like in some embodiments. The display 13 is used for displaying information processed in the electronic device 1 and for displaying a visual work interface, for example displaying the results of data statistics.
The network interface 14 may alternatively comprise a standard wired interface, a wireless interface, such as a WI-FI interface, which network interface 14 is typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
Fig. 3 shows only the electronic device 1 with components 11-14 and rule screening program 10, but it is understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
Optionally, the electronic device 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
The electronic device 1 may further comprise Radio Frequency (RF) circuits, sensors and audio circuits etc., which are not described here.
In the above embodiment, the processor 12 may implement the following steps when executing the impairment rule screening program 10 stored in the memory 11:
Reading a to-be-damaged item from a preset database, and matching the to-be-damaged item with a damage rule in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; wherein the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule;
scoring the triggered damage assessment rule based on a preset first calculation rule, and scoring the non-triggered damage assessment rule based on a preset second calculation rule to obtain scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule;
Feeding back the triggered loss assessment rules and the sorting results of the non-triggered loss assessment rules based on the grading values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set;
And executing union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, storing the target loss assessment rule set into the loss assessment rule engine, and feeding back all loss assessment rules of the target loss assessment rule set to a preset user.
The storage device may be the memory 11 of the electronic device 1, or may be another storage device communicatively connected to the electronic device 1.
For a detailed description of the above steps, please refer to the functional block diagram of the embodiment of the loss rule screening apparatus 100 shown in fig. 2 and the flowchart of the embodiment of the loss rule screening method based on artificial intelligence shown in fig. 1.
Furthermore, the embodiment of the invention also provides a computer readable medium, which can be nonvolatile or volatile. The computer readable medium may be any one or any combination of several of a hard disk, a multimedia card, an SD card, a flash memory card, SMC, a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a portable compact disc read only memory (CD-ROM), a USB memory, and the like. The computer readable medium includes a data storage area and a program storage area, the data storage area stores data created according to the use of blockchain nodes, the program storage area stores a lossy rule screening program 10, and the rule screening program 10 when executed by a processor realizes the following operations:
Reading a to-be-damaged item from a preset database, and matching the to-be-damaged item with a damage rule in a preset damage rule engine to obtain a triggered damage rule set and an un-triggered damage rule set of the to-be-damaged item; wherein the triggered damage assessment rule set comprises at least one triggered damage assessment rule, and the non-triggered damage assessment rule set comprises at least one non-triggered damage assessment rule;
scoring the triggered damage assessment rule based on a preset first calculation rule, and scoring the non-triggered damage assessment rule based on a preset second calculation rule to obtain scoring values of the triggered damage assessment rule and the non-triggered damage assessment rule;
Feeding back the triggered loss assessment rules and the sorting results of the non-triggered loss assessment rules based on the grading values to a first user, receiving feedback information sent by the first user based on the sorting results, selecting a first preset number of triggered loss assessment rules as a first candidate rule set according to the feedback information, and selecting a second preset number of non-triggered loss assessment rules as a second candidate rule set;
And executing union operation on the first candidate rule set and the second candidate rule set to obtain a target loss assessment rule set, storing the target loss assessment rule set into the loss assessment rule engine, and feeding back all loss assessment rules of the target loss assessment rule set to a preset user.
The embodiment of the computer readable medium of the present invention is substantially the same as the embodiment of the loss rule screening method based on artificial intelligence, and will not be described herein.
In another embodiment, the artificial intelligence-based loss rule screening method provided by the invention further ensures the privacy and security of all the data, and the data can be stored in a node of a blockchain. Such as a scoring value, a target impairment rule set, which may all be stored in the blockchain node.
It should be noted that, the blockchain referred to in the present invention is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a medium as described above (e.g. ROM/RAM, magnetic disk, optical disk), comprising instructions for causing a terminal device (which may be a mobile phone, a computer, an electronic device, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.