Household appliance industry repair system and method based on large model

Abstract

The invention discloses a household appliance industry repair system and method based on a large model. The system comprises a data acquisition module, a data processing module and a maintenance scheduling module. Relates to the technical field of household appliance repair, and solves the technical problem of low after-sale efficiency of household appliance repair in the prior art. According to the invention, the load state of each maintenance network is determined based on the repair amount change characteristic value and the repair amount predicted value; obtaining a service score corresponding to each maintenance network based on the basic information of the plurality of maintenance networks; and determining an optimal repair scheme based on the fault type of the abnormal household electrical appliance, the load state of each maintenance network and the service score. According to the method, the equipment operation data of the abnormal household electrical appliances, the environmental data in the after-sales area and the repair amount are comprehensively analyzed, the load state and the service score of each maintenance network point are evaluated, and then the optimal repair scheme is formulated, so that quick response and efficient processing are ensured, and the customer satisfaction and the maintenance efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of home appliance repair, and specifically is a home appliance industry repair system and method based on a large model. Background Art

[0002] In the rapidly developing home appliance industry, the usage of home appliances is increasing day by day, and the demand for repairs is also increasing. After-sales service has become one of the important indicators to measure the competitiveness of enterprises. The traditional after-sales service process of home appliances is complicated and inefficient, and it is difficult to meet the needs of modern consumers for fast response and high-quality services. Therefore, the development of a new after-sales system and method for the home appliance industry that can simplify the after-sales process and improve service efficiency and quality has become an urgent problem to be solved in the current home appliance industry.

[0003] Most of the existing home appliance repair solutions require users to send the fault status of abnormal home appliances to the home appliance repair platform through telephone or APP, and the home appliance repair platform generates corresponding repair work orders based on the fault status. However, in actual situations, some home appliances are affected by the external environment during operation. For example, the probability of air conditioners failing is relatively higher in hot weather, and the corresponding number of reports will also increase; when the number of repairs exceeds the after-sales capacity limit of the maintenance outlets, it is difficult for the maintenance outlets to arrange maintenance workers to repair the abnormal home appliances in a timely manner, resulting in low after-sales efficiency of home appliance repairs and low user satisfaction.

[0004] The present invention proposes a large model-based home appliance industry repair reporting system and method to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a home appliance industry repair reporting system and method based on a large model, which is used to solve the technical problems that the prior art solutions make it difficult to arrange maintenance workers to repair abnormal home appliances in a timely manner, resulting in low after-sales efficiency of home appliance repair reports and low user satisfaction.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a large-model-based household appliance industry repair reporting system, comprising: a data processing module, and a data acquisition module and a maintenance scheduling module connected thereto;

[0007] The data collection module is used to collect equipment operation data of abnormal household appliances; obtain environmental data, repair volume and basic information of maintenance outlets in several after-sales areas; wherein each after-sales area includes a maintenance outlet, and the basic information includes the number of maintenance workers corresponding to different skill levels, the number of returns for repair and the number of complaints;

[0008] The data processing module is used to determine the fault type of abnormal household appliances based on the equipment operation data; input the environmental data and the repair volume into the repair volume prediction model to obtain the repair volume prediction value; determine the load status of each maintenance outlet based on the repair volume prediction value and the repair volume of several consecutive cycles; obtain the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets; wherein the repair volume prediction model is constructed based on the artificial intelligence model;

[0009] The maintenance scheduling module is used to determine the optimal repair plan based on the fault type of abnormal home appliances, the load status of each maintenance network point and the service score.

[0010] Preferably, the household appliance industry repair reporting system based on a large model further includes a fault type database, and the fault type database is used to store the mapping relationship between the operating characteristics of abnormal household appliances and the fault types.

[0011] Preferably, determining the fault type of the abnormal household appliance based on the device operation data includes:

[0012] The corresponding operation characteristics are extracted from the equipment operation data of the abnormal home appliance, and the operation characteristics are input into the fault type database for matching to obtain the fault type corresponding to the abnormal home appliance.

[0013] Preferably, the method of determining the load status of each maintenance network point based on the predicted value of the repair quantity and the repair quantity of several consecutive periods includes:

[0014] A1: Extract the predicted value of the repair volume of the maintenance outlets in each after-sales area and the repair volume of several consecutive cycles, and calculate the characteristic value of the repair volume change of each maintenance outlet based on the repair volume of several consecutive cycles;

[0015] A2: Determine whether the predicted value of the repair volume is greater than the preset repair volume threshold; if yes, mark the first load label of the corresponding maintenance outlet as 1; if no, mark the first load label of the corresponding maintenance outlet as 0;

[0016] A3: Determine whether the characteristic value of the change in the amount of repair reports is a negative number; if yes, mark the second load label of the corresponding maintenance outlet as 0; if no, jump to A4;

[0017] A4: Determine whether the characteristic value of the repair quantity change is greater than a preset characteristic change threshold; if yes, mark the second load label of the corresponding maintenance outlet as 1; if no, mark the second load label of the corresponding maintenance outlet as 0;

[0018] A5: Calculate the sum of the first load label and the second load label of each maintenance network point, and mark it as the load characteristic value;

[0019] A6: Determine whether the load characteristic value is greater than 1; if yes, mark the load state of the corresponding maintenance network as the first-level load state; if no, jump to A7;

[0020] A7: Determine whether the load characteristic value is equal to 1; if yes, mark the load state of the corresponding maintenance network point as the second-level load state; if no, mark the load state of the corresponding maintenance network point as the third-level load state;

[0021] Among them, the load status includes primary load status, secondary load status and tertiary load status, and the primary load status>secondary load status>tertiary load status.

[0022] Preferably, the calculation of the characteristic value of the change in the number of repair reports of each maintenance network point based on the number of repair reports in a plurality of consecutive periods includes:

[0023] The number of repair reports from maintenance outlets in each after-sales area for several consecutive periods is extracted, and the repair reports for several consecutive periods are linearly fitted to obtain the repair report volume change curve of the maintenance outlets in each after-sales area; the first-order derivative function of the repair report volume change curve is calculated to obtain the repair report volume derivative function; the difference between the maximum function value and the minimum function value of the repair report volume derivative function is calculated to obtain the repair report volume change characteristic value corresponding to the maintenance outlets in each after-sales area.

[0024] Preferably, the repair volume prediction model is constructed based on an artificial intelligence model, including:

[0025] Obtain environmental data and repair volume of maintenance outlets in each after-sales area within several consecutive periods, and integrate the environmental data and the corresponding repair volume into several groups of training data and test data; use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model, and finally obtain a repair volume prediction model with environmental data as input and predicted repair volume as output; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0026] It should be noted that environmental data includes outdoor temperature, indoor temperature, humidity, wind speed and sunlight exposure time.

[0027] Preferably, the obtaining of the service score corresponding to each maintenance outlet based on the basic information of the plurality of maintenance outlets includes:

[0028] Extract the basic information of each maintenance outlet; through the formula Calculate the service score FWPi of maintenance outlet i; where aij is the influence coefficient corresponding to proficiency level j in maintenance outlet i, RSij is the number of maintenance workers corresponding to proficiency level j in maintenance outlet i, FXCi is the number of returns for repair at maintenance outlet i, and TSCi is the number of complaints at maintenance outlet i; α, β, b1, and b2 are all proportional coefficients greater than 0; i = 1, 2, …, n, where n is the total number of maintenance outlets; j = 1, 2, …, m, where m is the total number of categories of proficiency levels in maintenance outlet i.

[0029] Preferably, the determining of the optimal repair solution based on the fault type of the abnormal household appliance, the load status of each maintenance outlet and the service score includes:

[0030] T1: Extract the fault type of abnormal home appliances and the service score of each maintenance outlet; the fault type includes remote repair fault and offline repair fault;

[0031] T2: Determine whether the fault type of the abnormal home appliance is a remote repair fault; if so, the abnormal home appliance will be repaired remotely by a maintenance outlet in the after-sales area where the abnormal home appliance is located; if not, jump to T3;

[0032] T3: Determine whether the load status of the maintenance outlets in the after-sales area where the abnormal home appliance is located is a first-level load status; if yes, determine the target maintenance outlet based on the load status and service scores of several adjacent maintenance outlets, and the target maintenance outlet will arrange maintenance workers to perform on-site maintenance; if no, the maintenance outlets in the after-sales area where the abnormal home appliance is located will arrange maintenance workers to perform on-site maintenance;

[0033] Among them, adjacent repair outlets refer to several repair outlets adjacent to the after-sales area where the abnormal home appliance is located.

[0034] Preferably, the step of determining a target maintenance network point based on the load status and service scores of a plurality of adjacent maintenance network points includes:

[0035] H1: Extract the load status and service scores of several maintenance outlets adjacent to the maintenance outlets in the after-sales area where the abnormal home appliance is located, and mark the adjacent maintenance outlets as alternative maintenance outlets;

[0036] H2: Determine whether the load state of the candidate maintenance network point is the third-level load state; if yes, mark the corresponding candidate maintenance network point as a waiting maintenance network point; if no, mark the corresponding candidate maintenance network point as a busy maintenance network point;

[0037] H3: Mark the candidate maintenance outlet with the highest service score as the target maintenance outlet.

[0038] A second aspect of the present invention provides a method for reporting repairs in the home appliance industry based on a large model, comprising:

[0039] S1: Collect equipment operation data of abnormal home appliances; obtain basic information on environmental data, repair volume and repair outlets in several after-sales areas;

[0040] S2: Determine the fault type of abnormal home appliances based on the equipment operation data;

[0041] S3: Inputting environmental data and the amount of repair reports into a repair report prediction model to obtain a repair report prediction value;

[0042] S4: Determine the load status of each maintenance network point based on the characteristic value of the repair volume change and the predicted value of the repair volume;

[0043] S5: Obtaining the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets;

[0044] S6: Determine the optimal repair plan based on the fault type of the abnormal home appliance, the load status of each maintenance outlet and the service score.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention comprehensively analyzes the equipment operation data of abnormal household appliances, environmental data in the after-sales area, and the number of repair reports, accurately determines the fault type, and uses the repair report prediction model to estimate future repair reports, evaluate the load status and service score of each maintenance outlet, and then formulate the optimal repair plan. This method not only improves the accuracy and efficiency of fault diagnosis, but also balances the workload of each maintenance outlet and improves the overall service quality. By scientifically allocating resources, rapid response and efficient processing are ensured, which is conducive to improving customer satisfaction and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is an overall flow chart of the household appliance industry repair method based on the large model in the present invention;

[0049] Figure 2 It is a schematic diagram of the principle of the home appliance industry repair system based on the large model in the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1-Figure 2 , the first aspect of the present invention provides a large model-based home appliance industry repair system, including: a data processing module, and a data acquisition module and a maintenance scheduling module connected thereto;

[0052] Data collection module: used to collect equipment operation data of abnormal home appliances; obtain environmental data, repair volume and basic information of maintenance outlets in several after-sales areas; each after-sales area includes a maintenance outlet, and basic information includes the number of maintenance workers of different skill levels, the number of repairs and the number of complaints;

[0053] Data processing module: used to determine the fault type of abnormal household appliances based on equipment operation data; input environmental data and repair volume into the repair volume prediction model to obtain the repair volume prediction value; determine the load status of each maintenance outlet based on the repair volume prediction value and the repair volume of several consecutive cycles; obtain the corresponding service score of each maintenance outlet based on the basic information of several maintenance outlets; wherein, the repair volume prediction model is built based on the artificial intelligence model;

[0054] Maintenance scheduling module: used to determine the optimal repair plan based on the fault type of abnormal home appliances, the load status of each maintenance outlet and the service score.

[0055] In this embodiment, a large model-based home appliance industry repair system further includes a fault type database, which is used to store a mapping relationship between operating characteristics of abnormal home appliances and fault types.

[0056] In this embodiment, determining the fault type of the abnormal household appliance based on the device operation data includes:

[0057] The corresponding operation characteristics are extracted from the equipment operation data of the abnormal home appliance, and the operation characteristics are input into the fault type database for matching to obtain the fault type corresponding to the abnormal home appliance.

[0058] In this embodiment, the load status of each maintenance network point is determined based on the predicted value of the repair volume and the repair volume of several consecutive periods, including:

[0059] A1: Extract the predicted value of the repair volume of the maintenance outlets in each after-sales area and the repair volume of several consecutive cycles, and calculate the characteristic value of the repair volume change of each maintenance outlet based on the repair volume of several consecutive cycles;

[0060] A2: Determine whether the predicted value of the repair volume is greater than the preset repair volume threshold; if yes, mark the first load label of the corresponding maintenance outlet as 1; if no, mark the first load label of the corresponding maintenance outlet as 0;

[0061] A3: Determine whether the characteristic value of the change in the amount of repair reports is a negative number; if yes, mark the second load label of the corresponding maintenance outlet as 0; if no, jump to A4;

[0062] A4: Determine whether the characteristic value of the repair quantity change is greater than a preset characteristic change threshold; if yes, mark the second load label of the corresponding maintenance outlet as 1; if no, mark the second load label of the corresponding maintenance outlet as 0;

[0063] A5: Calculate the sum of the first load label and the second load label of each maintenance network point, and mark it as the load characteristic value;

[0064] A6: Determine whether the load characteristic value is greater than 1; if yes, mark the load state of the corresponding maintenance network as the first-level load state; if no, jump to A7;

[0065] A7: Determine whether the load characteristic value is equal to 1; if yes, mark the load state of the corresponding maintenance network point as the second-level load state; if no, mark the load state of the corresponding maintenance network point as the third-level load state;

[0066] Among them, the load status includes primary load status, secondary load status and tertiary load status, and the primary load status>secondary load status>tertiary load status.

[0067] Exemplarily, the repair volume prediction value corresponding to maintenance point 1 is set to 40, the repair volume change characteristic value is 8, the repair volume threshold is 30, and the repair volume change characteristic value is 5; since the repair volume prediction value of 40 is greater than the preset repair volume threshold of 30, the first load label of maintenance point 1 is marked as 1; since the repair volume change characteristic value of 8 is greater than the preset characteristic change threshold of 5, the second load label of the corresponding maintenance point is marked as 1; the sum of the first load label and the second load label of each maintenance point is calculated to obtain a load characteristic value of 2; since the load characteristic value is greater than 1, the load state of maintenance point 1 is marked as a first-level load state.

[0068] In this embodiment, the repair quantity variation characteristic value of each maintenance network point is calculated based on the repair quantity of several consecutive cycles, including:

[0069] The number of repair reports from maintenance outlets in each after-sales area for several consecutive periods is extracted, and the repair reports for several consecutive periods are linearly fitted to obtain the repair report volume change curve of the maintenance outlets in each after-sales area; the first-order derivative function of the repair report volume change curve is calculated to obtain the repair report volume derivative function; the difference between the maximum function value and the minimum function value of the repair report volume derivative function is calculated to obtain the repair report volume change characteristic value corresponding to the maintenance outlets in each after-sales area.

[0070] The present invention obtains a repair quantity variation curve of the maintenance outlets in each after-sales area by performing linear fitting on the repair quantity of the maintenance outlets in each after-sales area in several continuous cycles; derives the repair quantity variation curve to obtain a repair quantity derivative function, and extracts a repair quantity variation characteristic value from the repair quantity derivative function; the extracted repair quantity variation characteristic value can accurately reflect the repair quantity variation trend of each maintenance outlet, which is conducive to more accurately determining the load state of each maintenance outlet through the repair quantity variation characteristic value in the follow-up.

[0071] In this embodiment, the repair volume prediction model is constructed based on an artificial intelligence model, including:

[0072] Obtain environmental data and repair volume of maintenance outlets in each after-sales area within several consecutive periods, and integrate the environmental data and the corresponding repair volume into several groups of training data and test data; use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model, and finally obtain a repair volume prediction model with environmental data as input and predicted repair volume as output; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0073] It should be noted that environmental data includes outdoor temperature, indoor temperature, humidity, wind speed and sunlight exposure time.

[0074] The present invention obtains environmental data and repair volume of maintenance outlets in each after-sales area within several consecutive periods, and uses the environmental data and the corresponding repair volume to train an artificial intelligence model. After the training is completed, a repair volume prediction model is obtained. By inputting environmental data of several consecutive periods into the repair volume prediction model, a repair volume prediction value of the prediction period is obtained; the system is enabled to obtain the change of the repair volume of each maintenance outlet in advance, and determine the load state of each maintenance outlet according to the repair volume prediction value and the characteristic value of the repair volume change, thereby reducing the occurrence of untimely after-sales service follow-up after home appliance repair due to overload operation of the maintenance outlet, thereby helping to improve the processing efficiency of home appliance repair.

[0075] In this embodiment, the service score corresponding to each maintenance outlet is obtained based on the basic information of several maintenance outlets, including:

[0076] Extract the basic information of each maintenance outlet; through the formula Calculate the service score FWPi of maintenance outlet i; where aij is the influence coefficient corresponding to proficiency level j in maintenance outlet i, RSij is the number of maintenance workers corresponding to proficiency level j in maintenance outlet i, FXCi is the number of returns for repair at maintenance outlet i, and TSCi is the number of complaints at maintenance outlet i; α, β, b1, and b2 are all proportional coefficients greater than 0, and their specific values ​​are set by relevant experts based on experience; i = 1, 2, …, n, where n is the total number of maintenance outlets; j = 1, 2, …, m, where m is the total number of categories of proficiency levels in maintenance outlet i.

[0077] It should be noted that the values ​​of the proportional coefficients b1 and b2 are related to the selling price of the home appliance being repaired. When the selling price of the home appliance being repaired is higher, the corresponding values ​​of the proportional coefficients b1 and b2 are set to be larger; when the service score of the maintenance outlet is higher, it means that the after-sales guarantee level of the corresponding maintenance outlet is higher, and the efficiency of handling home appliance repairs can be improved; the influence coefficient aij of the proficiency level is set according to the working years of the maintenance workers in the maintenance outlets. When the working years of the maintenance workers are longer, the corresponding influence coefficient aij is set to be larger.

[0078] For example, the proportional coefficients α=0.7, β=100, b1=0.1, and b2=0.2 are set; the total number of categories of proficiency levels of maintenance outlet 1 is set to m=3, and the proficiency level of maintenance workers with less than 1 year of service experience is marked as 1, the proficiency level of maintenance workers with more than 1 year of service experience but less than 3 years of service experience is marked as 2, and the proficiency level of maintenance workers with more than 3 years of service experience is marked as 3;

[0079] Set the influence coefficient a11=2 and the number of maintenance workers RS11=5 for proficiency level 1, the influence coefficient a12=4 and the number of maintenance workers RS12=3 for proficiency level 2, and the influence coefficient a13=6 and the number of maintenance workers RS13=2 for proficiency level 3;

[0080] Set the number of repair returns for maintenance outlet 1 FXC1 = 8, and the number of complaints for maintenance outlet 1 TSC1 = 5; calculate through the formula to obtain the service score of maintenance outlet 1 FWP1≈40.33.

[0081] In this embodiment, the optimal repair solution is determined based on the fault type of the abnormal home appliance, the load status of each maintenance outlet, and the service score, including:

[0082] T1: Extract the fault type of abnormal home appliances and the service score of each maintenance outlet; the fault type includes remote repair fault and offline repair fault;

[0083] T2: Determine whether the fault type of the abnormal home appliance is a remote repair fault; if so, the abnormal home appliance will be repaired remotely by a maintenance outlet in the after-sales area where the abnormal home appliance is located; if not, jump to T3;

[0084] T3: Determine whether the load status of the maintenance outlets in the after-sales area where the abnormal home appliance is located is a first-level load status; if yes, determine the target maintenance outlet based on the load status and service scores of several adjacent maintenance outlets, and the target maintenance outlet will arrange maintenance workers to perform on-site maintenance; if no, the maintenance outlets in the after-sales area where the abnormal home appliance is located will arrange maintenance workers to perform on-site maintenance;

[0085] Among them, adjacent repair outlets refer to several repair outlets adjacent to the after-sales area where the abnormal home appliance is located.

[0086] The present invention classifies and identifies the fault types of abnormal household appliances, and dynamically allocates maintenance tasks in combination with the load status of maintenance outlets and service scores. For remote repair faults, local outlets are given priority to handle remotely to reduce manpower scheduling; for offline repair faults, intelligent decisions are made based on the load status of local outlets: if it is a first-level load, the target outlet is assigned based on the load and service scores of adjacent outlets to achieve cross-regional resource coordination; if it is a non-first-level load, the local outlet responds directly. This method optimizes the allocation of maintenance resources, reduces the risk of outlet overload, and reduces user waiting time through fault type classification processing and dynamic scheduling mechanism, while ensuring maintenance quality and user experience based on service scores, which is conducive to improving the response efficiency, resource utilization and customer satisfaction of after-sales service.

[0087] In this embodiment, the target maintenance network point is determined based on the load status and service scores of several adjacent maintenance network points, including:

[0088] H1: Extract the load status and service scores of several maintenance outlets adjacent to the maintenance outlets in the after-sales area where the abnormal home appliance is located, and mark the adjacent maintenance outlets as alternative maintenance outlets;

[0089] H2: Determine whether the load state of the candidate maintenance network point is the third-level load state; if yes, mark the corresponding candidate maintenance network point as a waiting maintenance network point; if no, mark the corresponding candidate maintenance network point as a busy maintenance network point;

[0090] H3: Mark the candidate maintenance outlet with the highest service score as the target maintenance outlet.

[0091] The present invention identifies the load and service status of the after-sales area where the abnormal home appliance is located and its adjacent maintenance outlets, and preferentially selects maintenance outlets that are not busy and have high service scores as target maintenance outlets. This method effectively shortens the maintenance response time, improves the efficiency and quality of maintenance services, and enhances user experience and satisfaction, which is of great significance for optimizing the resource allocation of the home appliance after-sales service network.

[0092] The second aspect of the present invention provides a method for reporting repairs in the home appliance industry based on a large model, comprising:

[0093] S1: Collect equipment operation data of abnormal home appliances; obtain basic information on environmental data, repair volume and repair outlets in several after-sales areas;

[0094] S2: Determine the fault type of abnormal home appliances based on the equipment operation data;

[0095] S3: Inputting environmental data and the amount of repair reports into a repair report prediction model to obtain a repair report prediction value;

[0096] S4: Determine the load status of each maintenance network point based on the characteristic value of the repair volume change and the predicted value of the repair volume;

[0097] S5: Obtaining the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets;

[0098] S6: Determine the optimal repair plan based on the fault type of the abnormal home appliance, the load status of each maintenance outlet and the service score.

[0099] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0100] Working principle of the present invention:

[0101] The present invention collects equipment operation data of abnormal household appliances; obtains environmental data, repair volume and basic information of maintenance outlets in several after-sales areas; determines the fault type of abnormal household appliances based on the equipment operation data; inputs environmental data and repair volume into a repair volume prediction model to obtain a repair volume prediction value; determines the load state of each maintenance outlet based on a repair volume change characteristic value and the repair volume prediction value; obtains the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets; and determines the optimal repair plan based on the fault type of the abnormal household appliances, the load state of each maintenance outlet and the service score.

[0102] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A home appliance industry repair system based on a large model, comprising: The data processing module, and the data acquisition module and maintenance scheduling module connected thereto are characterized in that: The data collection module is used to collect the equipment operation data of abnormal household appliances; obtain the environmental data, the number of repair reports and the basic information of the maintenance outlets in several after-sales areas; wherein each after-sales area includes a maintenance outlet; The data processing module is used to determine the fault type of abnormal household appliances based on the equipment operation data; input the environmental data and the repair volume into the repair volume prediction model to obtain the repair volume prediction value; determine the load status of each maintenance outlet based on the repair volume prediction value and the repair volume of several consecutive cycles; obtain the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets; wherein the repair volume prediction model is constructed based on the artificial intelligence model; The maintenance scheduling module is used to determine the optimal repair plan based on the fault type of abnormal home appliances, the load status of each maintenance network point and the service score.

2. A large model-based home appliance industry repair system according to claim 1, characterized in that: It also includes a fault type database, which is used to store the mapping relationship between the operation characteristics of abnormal household appliances and the fault types.

3. A large model-based home appliance industry repair system according to claim 2, characterized in that: The determining of the fault type of the abnormal household appliance based on the equipment operation data includes: The corresponding operation characteristics are extracted from the equipment operation data of the abnormal home appliance, and the operation characteristics are input into the fault type database for matching to obtain the fault type corresponding to the abnormal home appliance.

4. The home appliance industry repair system based on a large model according to claim 1, characterized in that: The method of determining the load status of each maintenance network point based on the predicted value of the repair quantity and the repair quantity of several consecutive cycles includes: A1: Extract the predicted value of the repair volume of the maintenance outlets in each after-sales area and the repair volume of several consecutive cycles, and calculate the characteristic value of the repair volume change of each maintenance outlet based on the repair volume of several consecutive cycles; A2: Determine whether the predicted value of the repair volume is greater than the preset repair volume threshold; if yes, mark the first load label of the corresponding maintenance outlet as 1; if no, mark the first load label of the corresponding maintenance outlet as 0; A3: Determine whether the characteristic value of the change in the amount of repair reports is a negative number; if yes, mark the second load label of the corresponding maintenance network point as 0; if no, jump to A4; A4: Determine whether the characteristic value of the repair quantity change is greater than a preset characteristic change threshold; if yes, mark the second load label of the corresponding maintenance outlet as 1; if no, mark the second load label of the corresponding maintenance outlet as 0; A5: Calculate the sum of the first load label and the second load label of each maintenance network point, and mark it as the load characteristic value; A6: Determine whether the load characteristic value is greater than 1; if yes, mark the load state of the corresponding maintenance network as the first-level load state; if no, jump to A7; A7: Determine whether the load characteristic value is equal to 1; if yes, mark the load state of the corresponding maintenance network point as the second-level load state; if no, mark the load state of the corresponding maintenance network point as the third-level load state; Among them, the load status includes primary load status, secondary load status and tertiary load status, and the primary load status>secondary load status>tertiary load status.

5. A large model-based home appliance industry repair system according to claim 4, characterized in that: The calculation of the repair quantity variation characteristic value of each maintenance network point based on the repair quantity of several consecutive cycles includes: The number of repair reports from maintenance outlets in each after-sales area for several consecutive periods is extracted, and the repair reports for several consecutive periods are linearly fitted to obtain the repair report volume change curve of the maintenance outlets in each after-sales area; the first-order derivative function of the repair report volume change curve is calculated to obtain the repair report volume derivative function; the difference between the maximum function value and the minimum function value of the repair report volume derivative function is calculated to obtain the repair report volume change characteristic value corresponding to the maintenance outlets in each after-sales area.

6. The home appliance industry repair system based on a large model according to claim 1, characterized in that: The repair volume prediction model is constructed based on an artificial intelligence model and includes: Obtain environmental data and repair volume of maintenance outlets in each after-sales area within several consecutive periods, and integrate the environmental data and the corresponding repair volume into several groups of training data and test data; use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model, and finally obtain a repair volume prediction model with environmental data as input and predicted repair volume as output; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

7. The home appliance industry repair system based on a large model according to claim 1, characterized in that: The obtaining of the service score corresponding to each maintenance outlet based on the basic information of the plurality of maintenance outlets includes: Extract the basic information of each maintenance outlet; through the formula Calculate the service score FWPi of maintenance outlet i; where aij is the influence coefficient corresponding to proficiency level j in maintenance outlet i, RSij is the number of maintenance workers corresponding to proficiency level j in maintenance outlet i, FXCi is the number of returns for repair at maintenance outlet i, and TSCi is the number of complaints at maintenance outlet i; α, β, b1, and b2 are all proportional coefficients greater than 0; i = 1, 2, …, n, where n is the total number of maintenance outlets; j = 1, 2, …, m, where m is the total number of categories of proficiency levels in maintenance outlet i.

8. The home appliance industry repair system based on a large model according to claim 1, characterized in that: The optimal repair solution is determined based on the fault type of abnormal household appliances, the load status of each maintenance outlet and the service score, including: T1: Extract the fault type of abnormal home appliances and the service score of each maintenance outlet; the fault type includes remote repair fault and offline repair fault; T2: Determine whether the fault type of the abnormal home appliance is a remote repair fault; if so, the abnormal home appliance will be repaired remotely by a maintenance outlet in the after-sales area where the abnormal home appliance is located; if not, jump to T3; T3: Determine whether the load status of the maintenance outlets in the after-sales area where the abnormal home appliance is located is a first-level load status; if yes, determine the target maintenance outlet based on the load status and service scores of several adjacent maintenance outlets, and the target maintenance outlet will arrange maintenance workers to perform on-site maintenance; if no, the maintenance outlets in the after-sales area where the abnormal home appliance is located will arrange maintenance workers to perform on-site maintenance; Among them, adjacent repair outlets refer to several repair outlets adjacent to the after-sales area where the abnormal home appliance is located.

9. A large model-based home appliance industry repair system according to claim 8, characterized in that: The method of determining a target maintenance network point based on the load status and service scores of a plurality of adjacent maintenance network points includes: H1: Extract the load status and service scores of several maintenance outlets adjacent to the maintenance outlets in the after-sales area where the abnormal home appliance is located, and mark the adjacent maintenance outlets as alternative maintenance outlets; H2: Determine whether the load state of the candidate maintenance network point is the third-level load state; if yes, mark the corresponding candidate maintenance network point as a waiting maintenance network point; if no, mark the corresponding candidate maintenance network point as a busy maintenance network point; H3: Mark the candidate maintenance outlet with the highest service score as the target maintenance outlet.

10. A method for reporting repairs in the home appliance industry based on a large model, based on the operation of a system for reporting repairs in the home appliance industry based on a large model as claimed in any one of claims 1 to 9, characterized in that: include: S1: Collect equipment operation data of abnormal home appliances; Obtain basic information on environmental data, repair volume and repair outlets in several after-sales areas; S2: Determine the fault type of abnormal home appliances based on the equipment operation data; S3: Inputting environmental data and the amount of repair reports into a repair report prediction model to obtain a repair report prediction value; S4: Determine the load status of each maintenance network point based on the characteristic value of the repair volume change and the predicted value of the repair volume; S5: Obtaining the service score corresponding to each maintenance outlet based on the basic information of several maintenance outlets; S6: Determine the optimal repair plan based on the fault type of the abnormal home appliance, the load status of each maintenance outlet and the service score.

Images