Intelligent pet service management system based on big data analysis

Abstract

The invention discloses a pet service intelligent management system based on big data analysis, and particularly relates to the technical field of service management, shops of an online platform are screened through pet service types, appointment dates and pet images required by target users, and a second target shop set is obtained; for each shop in the second target shop set, obtaining the length of a reservable time period and the number of times of service of the pet service type required by the target user by the employee in the reservable time period, and obtaining the priority index of the corresponding shop in combination with the matching degree of the corresponding shop; and arranging the shops in the second target shop set according to the descending order of the priority indexes, and pushing the shops to the customer for the customer to perform reservation service, so that accurate recommendation can be performed according to specific demands of pets, reservation disorder is reduced, proper shops can be selected, dynamic adjustment and priority ranking can be performed, and the user experience is improved. Therefore, the confusion of the customer during selection is reduced, and the service experience and satisfaction are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of service management, and in particular to an intelligent management system for pet services based on big data analysis. Background Art

[0002] In recent years, more and more people choose to keep pets. Against this background, the pet service industry has emerged. More and more cities have opened professional pet service stores for users to choose from. At the same time, in order to ensure the convenience of services, more and more stores choose to provide appointment services on the platform to ensure the efficiency and timeliness of pet services. Through these online platforms, pet owners can easily view various service items and choose the appropriate time and place to make an appointment, which not only saves time but also improves the quality of service.

[0003] However, existing online pet service reservation platforms usually rely on users to manually search and filter stores, but lack an intelligent matching mechanism and are unable to make accurate recommendations based on the specific needs of pets, which may lead to reservation confusion and the selection of inappropriate stores. At the same time, the lack of dynamic adjustment and priority sorting functions increases customer confusion when making choices and affects service experience and satisfaction. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and provide an intelligent management system for pet services based on big data analysis.

[0005] The present invention proposes a pet service intelligent management system based on big data analysis, the system comprising:

[0006] First target module: obtain the pet service type and reservation date required by the target user, and perform a preliminary screening of the stores on the online platform according to the required pet service type and reservation date to obtain the first target store set;

[0007] Second target module: obtain pet images, identify pet features, determine the matching degree of each store based on the pet features and the service features of the stores in the first target store set, and perform secondary screening on the first target store set based on the matching degree and a preset matching degree threshold to obtain a second target store set;

[0008] Priority index module: for each store in the second target store set, the length of the available reservation time period and the number of times the employees provide the pet service type required by the target user during the available reservation time period are obtained, and combined with the matching degree of the corresponding store, the priority index of the corresponding store is obtained;

[0009] Reservation management module: Arrange the stores in the second target store set in descending order of priority index and push them to customers for reservation services.

[0010] Optionally, the second target module includes:

[0011] First membership module: by using a preset feature recognition model, all feature types of the pet in the pet image and the specific features corresponding to each feature type are identified, and for each feature type, a fuzzy set is defined, each element in the fuzzy set corresponds to a specific feature, and a membership is defined for any element in the fuzzy set, and the membership of the specific feature corresponding to each feature type of the pet is used as the first membership of the corresponding feature type;

[0012] Service Excellence Index Module: Obtain the total number of services, service frequency, favorable comment rate and service growth rate for each specific feature type corresponding to the historical service data of each store in the first target store set, and normalize the total number of services, service frequency, favorable comment rate and service growth rate to obtain the service excellence index. The calculation formula is: Dxc = a1×cv+a2×cx+a3×cg+a4×hk, where Dxc is the service excellence index, cv, cx, cg, hk are the total number of services, service frequency, favorable comment rate and service growth rate after normalization, a1, a2, a3, a4 are the preset weights of cv, cx, cg, hk, and a1, a2, a3, a4 are all greater than 0;

[0013] Matching degree module: Calculate the matching degree of each store based on the first degree of membership corresponding to each feature type and the service excellence index corresponding to the store.

[0014] Optionally, the matching module includes:

[0015] Matching value module: taking the service excellence index of the specific feature corresponding to each feature type of the store as the second membership degree, and multiplying the first membership degree by the second membership degree to obtain the matching value of each corresponding feature type;

[0016] Matching degree calculation module: add up the matching values ​​of all feature types of each store in the first target store set to obtain the matching degree of the corresponding store.

[0017] Optionally, the second target module further includes:

[0018] Comparison module: compares the matching degree of each store in the first target store set with a preset matching degree threshold;

[0019] Selectable module: If the matching degree is greater than the preset matching degree threshold, the corresponding store will be marked as a selectable store;

[0020] The second target store set determination module takes all selectable stores in the first target store set as the second target store set.

[0021] Optionally, the priority index module includes a fatigue index module, a service capability index module and a priority index calculation module;

[0022] The fatigue index module is used to calculate the fatigue index of the scheduling staff of the appointment service of each store in the second target store set;

[0023] The service capability index module is used to calculate the service capability index of the scheduling staff for appointment service in each store in the second target store set;

[0024] The priority index calculation module is used to calculate the priority index of the corresponding store according to the fatigue index, service capability index, length of the corresponding reservable time period and the matching degree of the store of each store in the second target store set.

[0025] Optionally, the fatigue index module is specifically used for:

[0026] Determine the staff on duty who provide appointment services in the appointment time period for each store in the second target store concentration, and obtain the scheduled working hours, the number and type of scheduled services, and the total scheduled rest time of the corresponding scheduled staff on the day before the appointment time period, and perform normalization processing to obtain the fatigue index of the corresponding scheduled staff. The calculation formula is:

[0027]

[0028] Where Qv is the fatigue index of the corresponding store scheduling staff, yu and nc are the total scheduled working hours and scheduled rest time of the scheduling staff on the day, respectively, and tu i is the type of the i-th service that has been booked, ω i is the preset fatigue value corresponding to the type of the i-th scheduled service, and k is the total number of scheduled services.

[0029] Optionally, the service capability index module is specifically used to:

[0030] Obtain the second target store set, the staff on duty for appointment service in each store during the appointment time period, the total number of services, service completion rate and service satisfaction rate for the pet service type required by the target user, and normalize the total number of services, service completion rate and service satisfaction rate to obtain the service capability index. The calculation formula is: Where Fg is the service capability index, tr, th, and te are the total number of services, service completion rate, and service satisfaction rate after normalization.

[0031] Optionally, the priority index calculation module is specifically used to:

[0032] For each store in the second target store set, the length of the available reservation time period is normalized, and the priority index of the corresponding store is obtained by combining the fatigue index of the scheduling staff, the employee service ability index and the matching degree of the corresponding store. The calculation formula is:

[0033]

[0034] Where Qbr is the priority index of the corresponding store, Ax is the length of the normalized reservable time period, Qv, Fg, and Wf are the fatigue index of the scheduling staff, the employee service ability index, and the matching degree of the corresponding store, respectively; c1, c2, c3, and c4 are the preset proportional coefficients of Ax, Qv, Fg, and Wf, respectively, and c1, c2, c3, and c4 are all greater than 0.

[0035] Beneficial effects of the present invention:

[0036] The present invention proposes an intelligent management system for pet services based on big data analysis, which obtains the type of pet service and reservation date required by a target user, and performs a primary screening of stores on an online platform according to the required type of pet service and reservation date to obtain a first target store set; then obtains a pet image, identifies the characteristics of the pet, and determines the matching degree of each store according to the characteristics of the pet and the service characteristics of stores in the first target store set, and performs a secondary screening of the first target store set according to the matching degree and a preset matching degree threshold to obtain a second target store set; for each store in the second target store set, obtains the length of the reservable time period and the number of services provided by employees for the type of pet service required by the target user during the reservable time period, and obtains the priority index of the corresponding store in combination with the matching degree of the corresponding store; arranges the stores in the second target store set in order of priority index from large to small and pushes them to customers for customers to make reservations for services, so that accurate recommendations can be made according to the specific needs of the pet, reducing reservation confusion, and selecting suitable stores, while enabling dynamic adjustment and priority sorting, reducing customer confusion when choosing, and ensuring service experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below in conjunction with the accompanying drawings.

[0038] Figure 1 This is a framework diagram of the pet service intelligent management system based on big data analysis. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0041] The embodiment of the present invention provides a pet service intelligent management system based on big data analysis. Figure 1 , Figure 1 This is a framework diagram of a pet service intelligent management system based on big data analysis provided by an embodiment of the present invention. The system includes:

[0042] First target module: obtain the pet service type and reservation date required by the target user, and perform a preliminary screening of the stores on the online platform according to the required pet service type and reservation date to obtain the first target store set;

[0043] Second target module: obtain pet images, identify pet features, determine the matching degree of each store based on the pet features and the service features of the stores in the first target store set, and perform secondary screening on the first target store set based on the matching degree and a preset matching degree threshold to obtain a second target store set;

[0044] Priority index module: for each store in the second target store set, the length of the available reservation time period and the number of times the employees provide the pet service type required by the target user during the available reservation time period are obtained, and combined with the matching degree of the corresponding store, the priority index of the corresponding store is obtained;

[0045] Reservation management module: Arrange the stores in the second target store set in descending order of priority index and push them to customers for reservation services.

[0046] The pet service intelligent management system based on big data analysis provided by the embodiment of the present invention can make accurate recommendations based on the specific needs of the pet, reduce reservation confusion, and select suitable stores. At the same time, it can dynamically adjust and prioritize, reducing customer confusion when making choices and ensuring service experience and satisfaction.

[0047] In one embodiment, the online platform stores are initially screened based on the required pet service type and appointment date. For example, if a user needs to make an appointment for a bathing service for their pet dog and chooses the appointment date as next Friday, all pet service stores on the online platform will be retrieved first, and then screened based on the service type and available appointment date of each store; specifically, the system will filter out all stores that provide bathing services and check the availability of these stores next Friday. If some stores do not provide bathing services or are full on that date, they will be excluded; after this round of initial screening, the user will obtain a collection of all stores that can provide bathing services on the specified date; this process not only improves efficiency, but also ensures that users can quickly find service stores that meet their needs, thus laying the foundation for subsequent matching and appointments.

[0048] In one embodiment, the second target module includes:

[0049] First membership module: by using a preset feature recognition model, all feature types of the pet in the pet image and the specific features corresponding to each feature type are identified, and for each feature type, a fuzzy set is defined, each element in the fuzzy set corresponds to a specific feature, and a membership is defined for any element in the fuzzy set, and the membership of the specific feature corresponding to each feature type of the pet is used as the first membership of the corresponding feature type;

[0050] Service Excellence Index Module: Obtain the total number of services, service frequency, favorable comment rate and service growth rate for each specific feature type corresponding to the historical service data of each store in the first target store set, and normalize the total number of services, service frequency, favorable comment rate and service growth rate to obtain the service excellence index. The calculation formula is: Dxc = a1×cv+a2×cx+a3×cg+a4×hk, where Dxc is the service excellence index, cv, cx, cg, hk are the total number of services, service frequency, favorable comment rate and service growth rate after normalization, a1, a2, a3, a4 are the preset weights of cv, cx, cg, hk, and a1, a2, a3, a4 are all greater than 0;

[0051] Matching degree module: Calculate the matching degree of each store based on the first degree of membership corresponding to each feature type and the service excellence index corresponding to the store.

[0052] In one embodiment, the matching module includes:

[0053] Matching value module: taking the service excellence index of the specific feature corresponding to each feature type of the store as the second membership degree, and multiplying the first membership degree by the second membership degree to obtain the matching value of each corresponding feature type;

[0054] Matching degree calculation module: add up the matching values ​​of all feature types of each store in the first target store set to obtain the matching degree of the corresponding store.

[0055] It should be noted that the above steps are illustrated by examples:

[0056] Step 1: Pet feature recognition and fuzzy set definition:

[0057] For example: provide a bathing service to a pet dog and identify the pet characteristics of the pet dog, assuming that the pet characteristics are body shape and hair length;

[0058] Through image recognition, it is determined that the pet is a medium-sized dog (body size) with long hair (hair length); for example, the pet features are body size and hair length;

[0059] Fuzzy sets are defined for these features, such as:

[0060] Fuzzy set of body size: small dogs, medium dogs, large dogs. Each category has a degree of membership. For example, the system believes that there is a 0.8 probability that this dog is a medium-sized dog.

[0061] Hair fuzzy set: short hair, medium-long hair, long hair; image analysis shows that the pet's hair is long hair, with a membership degree of 0.9.

[0062] These degrees of membership are called the second degrees of membership and are 0.8 (body size) and 0.9 (hair length);

[0063] Step 2: Store service data analysis and service excellence index calculation;

[0064] Extract the historical service data of each store from the first target store set:

[0065] For example, in the past, Store A provided bathing services for medium-sized dogs 150 times, with a service frequency of 3 times per day, a favorable review rate of 95%, and a service growth rate of 5%;

[0066] For long-haired pets, the historical data of trimming services provided by Store A shows that the total number of times is 120, the frequency is 2.5 times / day, the praise rate is 90%, and the growth rate is 4%;

[0067] Normalize these data and assume that: Dxc 体型 =0.85; Dxc 毛发 =0.78;

[0068] These indices represent the capabilities and performance of Shop A for bathing and long-hair trimming services for medium-sized dogs;

[0069] Step 3: Calculate store matching value:

[0070] Multiply the pet's first degree of membership by the store's service excellence index:

[0071] Size matching value = 0.8 (pet affiliation) × 0.85 (service excellence index) = 0.68;

[0072] Hair matching value = 0.9 (pet membership) × 0.78 (service excellence index) = 0.702;

[0073] Step 4: Comprehensive matching evaluation:

[0074] Adding the two matching values ​​together, we get the overall matching degree of store A: 0.68+0.702=1.382.

[0075] In one implementation, the above method combines the concepts of fuzzy sets and service excellence index, and the calculation of membership makes the recommendation more accurate and intelligent; the use of fuzzy sets allows a certain flexibility and fault tolerance to be introduced when processing pet features, rather than requiring a complete match. For example, a medium-sized dog may have some overlapping features between "small dog" and "large dog", and fuzzy sets can reflect this fuzziness and improve the accuracy of matching; membership quantifies pet features, allowing the system to handle the different needs of pets more delicately; the service excellence index is based on the store's historical service performance, comprehensively considering multiple factors such as the number of services, frequency, praise rate and growth rate, and provides a quantitative evaluation of the store's service capabilities; by multiplying the pet's feature membership with the store's service excellence index, the matching calculation can not only reflect the store's professionalism in serving this type of pet, but also provide a basis for recommendation in terms of service quality, customer feedback and service experience. This combined method allows the recommendation system to take into account the details of the pet's needs and to conduct objective screening based on the store's actual performance, ultimately improving the rationality of matching and the effectiveness of recommendations, and optimizing the customer's appointment experience.

[0076] It should be noted that a1, a2, a3, and a4 are set by professionals according to actual conditions. Generally, the sum of a1, a2, a3, and a4 is 1. For example, a1, a2, a3, and a4 can be 0.25, 0.25, 0.25, and 0.5, respectively, or other numbers, depending on the actual conditions, and no limitation or elaboration is made thereon.

[0077] It should be noted that the total number of services provided by the store, the frequency of services, the praise rate and the service growth rate can be directly obtained through the store’s historical service records on the online platform, or by other means, and no specific limitations or elaborations are made.

[0078] In one embodiment, the second target module further includes:

[0079] Comparison module: compares the matching degree of each store in the first target store set with a preset matching degree threshold;

[0080] Selectable module: If the matching degree is greater than the preset matching degree threshold, the corresponding store will be marked as a selectable store;

[0081] The second target store set determination module takes all selectable stores in the first target store set as the second target store set.

[0082] It should be noted that the preset matching threshold is set by professionals based on actual conditions and will not be elaborated or limited in detail.

[0083] In one implementation, by performing a secondary screening of the first target store set, combined with the matching degree and the preset matching degree threshold, the accuracy and efficiency of pet service reservations can be effectively improved. This process ensures that only those stores that are truly suitable for the user's pet needs are recommended, avoiding stores that do not meet the requirements from interfering with customer choices. This not only saves users' time, but also improves customer satisfaction and trust. At the same time, the setting of the preset matching degree threshold can be adjusted based on professional experience and data analysis, making the screening process more flexible and intelligent, and able to dynamically adapt to different pet types and service needs, thereby improving the overall service quality.

[0084] In one embodiment, the priority index module includes a fatigue index module, a service capability index module, and a priority index calculation module;

[0085] The fatigue index module is used to calculate the fatigue index of the scheduling staff of the appointment service in each store in the second target store set;

[0086] The service capability index module is used to calculate the service capability index of the scheduling staff for appointment service in each store in the second target store set;

[0087] The priority index calculation module is used to calculate the priority index of the corresponding store according to the fatigue index, service capability index, length of the corresponding appointment time period and the matching degree of the store of each store in the second target store set.

[0088] In one embodiment, the fatigue index module is specifically used to:

[0089] Determine the staff on duty who provide appointment services in the appointment time period for each store in the second target store concentration, and obtain the scheduled working hours, the number and type of scheduled services, and the total scheduled rest time of the corresponding scheduled staff on the day before the appointment time period, and perform normalization processing to obtain the fatigue index of the corresponding scheduled staff. The calculation formula is:

[0090]

[0091] Where Qv is the fatigue index of the corresponding store scheduling staff, yu and nc are the total scheduled working hours and scheduled rest time of the scheduling staff on the day, respectively, and tu i is the type of the i-th service that has been booked, ω i is the preset fatigue value corresponding to the type of the i-th scheduled service, and k is the total number of scheduled services.

[0092] The priority index of the corresponding store is obtained based on the fatigue index of the scheduling staff, the length of the appointment time period, the number of times the employees provide pet service types required by the target users during the appointment time period, and the matching degree of the corresponding store.

[0093] It should be noted that before the reservation time period, the scheduled working hours of the corresponding scheduled employees on that day, the number and types of reserved services, and the total scheduled rest time of each store can be directly obtained through the reservation records and typesetting status of each store on the online platform, or can be obtained in other ways, which are not limited or elaborated on. In addition, the preset fatigue values ​​corresponding to different service types are set by professionals based on the historical service experience of each store, which are not limited or elaborated on.

[0094] It should be noted that the greater the fatigue index of the store scheduling staff, the later the corresponding store's appointment service will be ranked, because the greater the fatigue index of the store scheduling staff, it means that the employee has experienced a long period of high-intensity service in the work before the appointment time period, or has not been able to get enough rest time; in this case, the employee's work efficiency, service quality and responsiveness may be affected, which can easily lead to fatigue and work errors. Therefore, when choosing appointment services, customers tend to choose stores with lower employee fatigue indexes, because employees in such stores can provide more efficient and professional services; relatively speaking, stores with higher fatigue indexes will have their appointment services ranked later to ensure customer experience and service quality. Such a ranking mechanism ensures that service providers can provide customers with the best service experience in a good working state.

[0095] In one embodiment, the service capability index module is specifically used to:

[0096] Obtain the second target store set, the staff on duty for appointment service in each store during the appointment time period, the total number of services, service completion rate and service satisfaction rate for the pet service type required by the target user, and normalize the total number of services, service completion rate and service satisfaction rate to obtain the service capability index. The calculation formula is: Where Fg is the service capability index, tr, th, and te are the total number of services, service completion rate, and service satisfaction rate after normalization.

[0097] The priority index of the corresponding store is obtained based on the fatigue index of the scheduling staff, the length of the appointment time period, the service capability index and the matching degree of the corresponding store.

[0098] It should be noted that the total number of services, service completion rate and service satisfaction rate of the types of pet services required by the target users can be directly obtained by the scheduling staff through the work records of the employees of each store on the online platform, or by other acquisition methods, which are not limited or elaborated on in detail;

[0099] It should be noted that when the service capability index of the store scheduling staff is higher, the corresponding store's appointment service ranking will be higher, because when the service capability index of the store scheduling staff is higher, the corresponding store's appointment service ranking will be higher, mainly because a high service capability index means that the employee has higher experience, efficiency and customer satisfaction in the required service type. This improvement in capability is directly reflected in the quality of service, and customers are more inclined to choose stores that can provide better services; high-capacity employees can meet customer needs faster and more accurately in appointment services, reduce errors and delays that may occur during the service process, and thus improve customer satisfaction and return rate. Therefore, considering the service capabilities of employees when prioritizing will help ensure that customers get a better service experience.

[0100] In one embodiment, the priority index calculation module is specifically used to:

[0101] For each store in the second target store set, the length of the available reservation time period is normalized, and the priority index of the corresponding store is obtained by combining the fatigue index of the scheduling staff, the employee service ability index and the matching degree of the corresponding store. The calculation formula is:

[0102]

[0103] Where Qbr is the priority index of the corresponding store, Ax is the length of the normalized reservable time period, Qv, Fg, and Wf are the fatigue index of the scheduling staff, the employee service ability index, and the matching degree of the corresponding store, respectively; c1, c2, c3, and c4 are the preset proportional coefficients of Ax, Qv, Fq, and Wf, respectively, and c1, c2, c3, and c4 are all greater than 0.

[0104] It should be noted that c1, c2, c3, and c4 are set by professionals according to actual conditions. Generally, the sum of c1, c2, c3, and c4 is 1. For example, c1, c2, c3, and c4 can be 0.2, 0.25, 0.3, and 0.25, respectively, or other numbers, without specific limitation.

[0105] In one implementation, the stores in the second target store set are arranged in descending order according to the priority index and pushed to customers. This process can help customers more intuitively identify the store that best meets their needs. The priority index ranking not only takes into account the store's service capabilities, employee fatigue and matching, but also integrates the length of the available appointment time period, thus providing a comprehensive reference basis; this intelligent sorting system can greatly reduce the decision-making time and complexity of customers when choosing a store, and avoid confusion and anxiety caused by information overload. In addition, customers are more likely to choose stores with high service quality, thereby improving the overall service experience and satisfaction.

[0106] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent pet service management system based on big data analysis, characterized in that: The system comprises: First target module: obtain the pet service type and reservation date required by the target user, and perform a preliminary screening of the stores on the online platform according to the required pet service type and reservation date to obtain the first target store set; Second target module: obtain pet images, identify pet features, determine the matching degree of each store based on the pet features and the service features of the stores in the first target store set, and perform secondary screening on the first target store set based on the matching degree and a preset matching degree threshold to obtain a second target store set; Priority index module: for each store in the second target store set, the length of the available reservation time period and the number of times the employees provide the pet service type required by the target user during the available reservation time period are obtained, and combined with the matching degree of the corresponding store, the priority index of the corresponding store is obtained; Reservation management module: Arrange the stores in the second target store set in descending order of priority index and push them to customers for reservation services.

2. The pet service intelligent management system based on big data analysis according to claim 1 is characterized in that: The second target module comprises: First membership module: by using a preset feature recognition model, all feature types of the pet in the pet image and the specific features corresponding to each feature type are identified, and for each feature type, a fuzzy set is defined, each element in the fuzzy set corresponds to a specific feature, and a membership is defined for any element in the fuzzy set, and the membership of the specific feature corresponding to each feature type of the pet is used as the first membership of the corresponding feature type; Service Excellence Index Module: Obtain the total number of services, service frequency, favorable comment rate and service growth rate for each specific feature type corresponding to the historical service data of each store in the first target store set, and normalize the total number of services, service frequency, favorable comment rate and service growth rate to obtain the service excellence index. The calculation formula is: Dxc = a1×cv+a2×cx+a3×cg+a4×hk, where Dxc is the service excellence index, cv, cx, cg, hk are the total number of services, service frequency, favorable comment rate and service growth rate after normalization, a1, a2, a3, a4 are the preset weights of cv, cx, cg, hk, and a1, a2, a3, a4 are all greater than 0; Matching degree module: Calculate the matching degree of each store based on the first degree of membership corresponding to each feature type and the service excellence index corresponding to the store.

3. The pet service intelligent management system based on big data analysis according to claim 2 is characterized in that: The matching degree module includes: Matching value module: taking the service excellence index of the specific feature corresponding to each feature type of the store as the second membership degree, and multiplying the first membership degree by the second membership degree to obtain the matching value of each corresponding feature type; Matching degree calculation module: add up the matching values ​​of all feature types of each store in the first target store set to obtain the matching degree of the corresponding store.

4. The pet service intelligent management system based on big data analysis according to claim 2 is characterized in that: The second target module also includes: Comparison module: compares the matching degree of each store in the first target store set with a preset matching degree threshold; Selectable module: If the matching degree is greater than the preset matching degree threshold, the corresponding store will be marked as a selectable store; The second target store set determination module takes all selectable stores in the first target store set as the second target store set.

5. The pet service intelligent management system based on big data analysis according to claim 1 is characterized in that: The priority index module includes a fatigue index module, a service capability index module and a priority index calculation module; The fatigue index module is used to calculate the fatigue index of the scheduling staff of the appointment service of each store in the second target store set; The service capability index module is used to calculate the service capability index of the scheduling staff for appointment service in each store in the second target store set; The priority index calculation module is used to calculate the priority index of the corresponding store according to the fatigue index, service capability index, length of the corresponding reservable time period and the matching degree of the store of each store in the second target store set.

6. The pet service intelligent management system based on big data analysis according to claim 5 is characterized in that: The fatigue index module is specifically used for: Determine the staff on duty who provide appointment services in the appointment time period for each store in the second target store concentration, and obtain the scheduled working hours, the number and type of scheduled services, and the total scheduled rest time of the corresponding scheduled staff on the day before the appointment time period, and perform normalization processing to obtain the fatigue index of the corresponding scheduled staff. The calculation formula is: Where Qv is the fatigue index of the corresponding store scheduling staff, yu and nc are the total scheduled working hours and scheduled rest time of the scheduling staff on the day, respectively, and tu i is the type of the i-th service that has been booked, ω i is the preset fatigue value corresponding to the type of the i-th scheduled service, and k is the total number of scheduled services.

7. The pet service intelligent management system based on big data analysis according to claim 5 is characterized in that: The service capability index module is specifically used for: Obtain the second target store set, the staff on duty for appointment service in each store during the appointment time period, the total number of services, service completion rate and service satisfaction rate for the pet service type required by the target user, and normalize the total number of services, service completion rate and service satisfaction rate to obtain the service capability index. The calculation formula is: Where Fg is the service capability index, tr, th, and te are the total number of services, service completion rate, and service satisfaction rate after normalization.

8. The pet service intelligent management system based on big data analysis according to claim 5 is characterized in that: The priority index calculation module is specifically used for: For each store in the second target store set, the length of the available reservation time period is normalized, and the priority index of the corresponding store is obtained by combining the fatigue index of the scheduling staff, the employee service ability index and the matching degree of the corresponding store. The calculation formula is: Where Qbr is the priority index of the corresponding store, Ax is the length of the normalized reservable time period, Qv, Fg, and Wf are the fatigue index of the scheduling staff, the employee service ability index, and the matching degree of the corresponding store, respectively; c1, c2, c3, and c4 are the preset proportional coefficients of Ax, Qv, Fg, and Wf, respectively, and c1, c2, c3, and c4 are all greater than 0.

Images