Store management system, method, device, medium and program product

Abstract

The invention discloses a store management system, method and device, a medium and a program product in the technical field of computers. According to the store management system provided by the invention, on the basis of customer comment data of each store, closed-loop processing of data is realized from data collection to analysis, processing, integration and recommendation, and finally, stores needing to recommend learning tasks and stores needing to be inspected are automatically determined, so that necessary data support is provided for store inspection; and the shop patrolling personnel can realize targeted management for the shops needing to recommend learning tasks and the shops needing to be checked, so that the management difficulty and the management workload of the shops are reduced.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a store management system, method, device, medium, and program product. Background Art

[0002] Currently, the management of multiple stores mostly relies on store inspectors. The workload of store inspectors is not only huge, but also due to the inability to conduct targeted store inspections, store inspectors need to be proficient in various operations, and the business requirements for store inspectors are relatively high, resulting in difficult store management.

[0003] Therefore, how to reduce the difficulty and workload of store management is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a store management system, method, device, medium, and program product to reduce the difficulty and workload of store management. The specific solutions are as follows:

[0005] In a first aspect, this application provides a store management system, including:

[0006] A data collection module for collecting customer review data of each store;

[0007] A data analysis module for determining the sentiment tendency and associated business inspection items of the customer review data of each store, and statistically analyzing the customer review data of each store to obtain corresponding statistical analysis data;

[0008] A data integration module for generating comprehensive evaluation information of the corresponding store based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store;

[0009] A data recommendation module for determining the stores that need to recommend learning tasks and the stores that need to be inspected based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store.

[0010] Optionally, the data collection module is used to:

[0011] Export the user evaluation information of each store from at least one channel;

[0012] Clean the exported user evaluation information, and after unifying the data format, map the user evaluation information to the store identifiers set by the current system to obtain the customer review data of each store.

[0013] Optionally, the data analysis module is used to:

[0014] Use a sentiment analysis model to process the customer review data of each store respectively to obtain the sentiment tendency of the corresponding store;

[0015] Use the content analysis model to process the customer review data of each store respectively, and obtain the business inspection items associated with the corresponding store;

[0016] Statistically analyze the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information of the customer review data of each store. At the same time, statistically analyze the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information by channel to obtain the corresponding statistical analysis data.

[0017] Optionally, it further includes:

[0018] An intelligent reply module, which is used to use the content generation model to generate corresponding reply texts for the customer review data of each store, and automatically reply with the reply texts according to the reply confirmation instruction.

[0019] Optionally, the data integration module is used for:

[0020] Statistically analyze the sentiment tendency, business inspection items, statistical analysis data, and past store inspection evaluation data corresponding to each store in the form of charts;

[0021] Use the corresponding chart statistical results as the comprehensive evaluation information of the corresponding store.

[0022] Optionally, the data recommendation module is used for:

[0023] Push corresponding learning tasks to the stores that need to recommend learning tasks;

[0024] Mark inspection prompt information for the stores that need to be inspected; the inspection prompt information includes at least one of the following: the business inspection items corresponding to the stores that need to be inspected, the customer review data associated with the business inspection items, and the past store inspection evaluation data corresponding to the stores that need to be inspected.

[0025] Optionally, it further includes:

[0026] A data query module, which is used to respond to a query instruction and query at least one of the customer review data, corresponding sentiment tendency, business inspection items, statistical analysis data, comprehensive evaluation information, pushed learning tasks, and past store inspection evaluation data of each store.

[0027] In a second aspect, the present application provides a store management method, including:

[0028] Collect the customer review data of each store;

[0029] Determine the sentiment tendency and associated business inspection items of the customer review data of each store, and statistically analyze the customer review data of each store to obtain the corresponding statistical analysis data;

[0030] Generate the comprehensive evaluation information of the corresponding store based on the sentiment tendency, business inspection items, and statistical analysis data of each store;

[0031] Based on the sentiment tendency, business inspection items, and statistical analysis data of each store, determine the stores that need to recommend learning tasks and the stores that need to be inspected.

[0032] Optionally, collect the customer review data of each store, including:

[0033] Export the user evaluation information of each store from at least one channel;

[0034] After cleaning the exported user evaluation information and unifying the data format, map the user evaluation information to the store identifiers set in the current system to obtain the customer review data of each store.

[0035] Optionally, determine the sentiment tendency and associated business inspection items of the customer review data of each store, and statistically analyze the customer review data of each store to obtain the corresponding statistical analysis data, including:

[0036] Use the sentiment analysis model to process the customer review data of each store respectively to obtain the sentiment tendency of the corresponding store;

[0037] Use the content analysis model to process the customer review data of each store respectively to obtain the business inspection items associated with the corresponding store;

[0038] Statistically analyze the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information of the customer review data of each store. At the same time, statistically analyze the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information by channel to obtain the corresponding statistical analysis data.

[0039] Optionally, it also includes:

[0040] Use the content generation model to generate the corresponding reply text for the customer review data of each store, and automatically reply with the reply text according to the reply confirmation instruction.

[0041] Optionally, generate the comprehensive evaluation information of the corresponding store based on the sentiment tendency, business inspection items, and statistical analysis data of each store, including:

[0042] Statistically analyze the sentiment tendency, business inspection items, statistical analysis data, and past store inspection evaluation data of each store in the form of a chart;

[0043] Take the corresponding chart statistical result as the comprehensive evaluation information of the corresponding store.

[0044] Optionally, it also includes:

[0045] Push corresponding learning tasks to the stores that need to be recommended for learning tasks;

[0046] Mark inspection prompt information for the stores that need to be inspected; the inspection prompt information includes at least one of the following: business inspection items corresponding to the stores to be inspected, customer review data associated with the business inspection items, and past store inspection evaluation data corresponding to the stores to be inspected.

[0047] Optionally, it further includes:

[0048] In response to a query instruction, query at least one of the customer review data, corresponding sentiment tendency, business inspection items, statistical analysis data, comprehensive evaluation information, pushed learning tasks, and past store inspection evaluation data of each store.

[0049] In a third aspect, the present application provides an electronic device, including:

[0050] A memory for storing a computer program;

[0051] A processor for executing the computer program to implement the aforementioned store management method.

[0052] In a fourth aspect, the present application provides a readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned store management method.

[0053] In a fifth aspect, the present application provides a computer program product including computer programs / instructions, and when the computer programs / instructions are executed by a processor, the steps of the aforementioned store management method are implemented.

[0054] As can be seen from the above solutions, the present application provides a store management system, including: a data collection module for collecting customer review data of each store; a data analysis module for determining the sentiment tendency of the customer review data of each store and the associated business inspection items, and statistically analyzing the customer review data of each store to obtain corresponding statistical analysis data; a data integration module for generating comprehensive evaluation information of the corresponding stores based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store; a data recommendation module for determining the stores that need to be recommended for learning tasks and the stores that need to be inspected based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store.

[0055] It can be seen that the store management system provided by this application can collect customer review data of each store by using the data collection module; determine the sentiment tendency of the customer review data of each store and the associated business inspection items by using the data analysis module, and statistically analyze the customer review data of each store to obtain corresponding statistical analysis data; generate comprehensive evaluation information of the corresponding store by using the data integration module based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store; determine the stores that need to recommend learning tasks and the stores that need to be inspected by using the data recommendation module based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store. Thus, based on the customer review data of each store, from data collection to analysis, processing, integration, and recommendation, a closed-loop processing of data is achieved, and finally the stores that need to recommend learning tasks and the stores that need to be inspected are automatically determined, providing necessary data support for store inspections; the store patrol personnel can achieve targeted management for the stores that need to recommend learning tasks and the stores that need to be inspected, reducing the store management difficulty and management workload.

[0056] Correspondingly, a store management method, device, medium, and program product provided by this application also have the above technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0058] Figure 1 Schematic diagram of a store management system disclosed in this application;

[0059] Figure 2 Schematic diagram of statistical data by channels disclosed in this application;

[0060] Figure 3 Schematic diagram of the chart statistical results of the sentiment tendency disclosed in this application;

[0061] Figure 4 Schematic diagram of the statistical results of high-frequency words disclosed in this application;

[0062] Figure 5 Schematic diagram of the statistical results such as the positive review rate corresponding to the store disclosed in this application;

[0063] Figure 6 Schematic diagram of the data statistics from the perspective of business inspection items disclosed in this application;

[0064] Figure 7Schematic diagram of a detailed page that can be viewed during store inspections disclosed in this application;

[0065] Figure 8 Schematic diagram of a closed-loop processing of data disclosed in this application. Detailed implementation manners

[0066] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0067] Currently, the management of multiple stores mostly relies on store inspection personnel. The store inspection personnel not only have a huge workload, but also need to be proficient in various operations due to the inability to conduct targeted store inspections, which requires relatively high business requirements for the store inspection personnel and causes difficulties in store management. For this reason, this application provides a store management solution that can reduce the difficulty and workload of store management.

[0068] See Figure 1 As shown, an embodiment of this application discloses a store management system, including: a data collection module, a data analysis module, a data integration module, and a data recommendation module.

[0069] The data collection module is used to collect customer review data of each store. Among them, the data collection module collects customer review data of each store from different channels. Specifically, it can enable the store management system to connect to the software interface of the channel for instant push, or use RPA technology to obtain data. RPA is a robotic process automation technology that can execute business processes by configuring automated software to simulate the actions of humans interacting in a software system. In one implementation manner, the specific process of the data collection module collecting customer review data of each store includes: exporting user evaluation information of each store from at least one channel; performing data cleaning on the exported user evaluation information (to remove redundant or duplicate data), and after unifying the data format, mapping the user evaluation information to the store identifiers set in the current system to obtain customer review data of each store. Mapping the user evaluation information to the store identifiers set in the current system can realize the collation and collection of evaluation data of the same store. If the identifiers set for each store in the channel are inconsistent with the store identifiers set in the current system, it is necessary to collate and collect the evaluation data for the same store. The store identifier can be a custom digital code or a code composed of other characters such as English letters, and is used to mark the uniqueness of each store.

[0070] The data analysis module is used to determine the sentiment tendency of the customer review data of each store and the associated business inspection items, and statistically analyze the customer review data of each store to obtain corresponding statistical analysis data. The data analysis module can be implemented with the help of various models or algorithms. For example, the data analysis module analyzes the sentiment tendency of the customer review data with the help of a sentiment analysis model. The sentiment tendency may include negative, positive, and neutral. In one embodiment, the specific process of the data analysis module analyzing data includes: using the sentiment analysis model to process the customer review data of each store separately to obtain the sentiment tendency of the corresponding store. Using the content analysis model to process the customer review data of each store separately to obtain the business inspection items associated with the corresponding store; the content analysis model is used to construct the association relationship between the customer review data of the store and the corresponding business inspection items. Statistically analyze the high-frequency words, incorrect words, number of comments, number of negative reviews, rate of negative reviews, and month-on-month information of the customer review data of each store, and at the same time, statistically analyze the high-frequency words, incorrect words, number of comments, number of negative reviews, rate of negative reviews, and month-on-month information by channel to obtain corresponding statistical analysis data. The various data obtained by channel statistics can refer to Figure 2 .

[0071] It should be noted that sentiment analysis models can be implemented based on dictionary methods, or based on machine learning and deep learning methods. Among them, dictionary-based methods rely on predefined vocabularies that contain words with positive or negative sentiment. By counting the number or weight of positive and negative words in the text, the overall sentiment tendency of the text can be obtained. Machine learning-based methods involve feature engineering, that is, extracting features useful for sentiment classification from the text, and then using these features to train machine learning models, such as support vector machines, naive Bayes classifiers, etc. Deep learning-based methods can use convolutional neural networks, recurrent neural networks, long short-term memory networks, etc. These models can automatically learn feature representations in text.

[0072] The data integration module is used to generate comprehensive evaluation information of the corresponding stores based on the emotional tendencies, business inspection items, and statistical analysis data corresponding to each store. In one embodiment, the data integration module is used to: compile statistics of the emotional tendencies, business inspection items, statistical analysis data, and previous store inspection evaluation data corresponding to each store in the form of charts; and use the corresponding chart statistics as the comprehensive evaluation information of the corresponding store. The chart statistics of emotional tendencies can be referred to Figure 3 , the high-frequency word statistics can be obtained according to Figure 4 , the corresponding statistical results of the praise rate of each store in the region can be referred to Figure 5 At the same time, data statistics can also be performed from the perspective of business inspection items (i.e., inspection item classification). For details, please refer to Figure 6 .

[0073] A data recommendation module is used to determine the stores that need to be recommended for learning tasks and the stores that need to be inspected based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store. Among them, the stores that need to be recommended for learning tasks and the stores that need to be inspected can be the same or different. In one implementation, the data recommendation module is also used to: push corresponding learning tasks to the stores that need to be recommended for learning tasks; mark inspection prompt information for the stores that need to be inspected; the inspection prompt information includes at least one of the following: the business inspection items corresponding to the stores that need to be inspected, the customer review data associated with the business inspection items, and the previous store inspection evaluation data corresponding to the stores that need to be inspected. The inspection prompt information marked for the stores that need to be inspected is used to prompt the inspectors of the corresponding stores with the key contents to be inspected when they conduct on-site inspections, so as to facilitate the on-site inspections; among them, the customer review data associated with the business inspection items to be inspected and the previous store inspection evaluation data corresponding to the stores that need to be inspected are provided for the inspectors to retrieve and query, so that the inspectors can evaluate the inspected stores from multiple perspectives.

[0074] In this embodiment, the store management system further includes: an intelligent reply module and a data query module. The intelligent reply module is used to generate corresponding reply texts for the customer review data of each store by using a content generation model, and automatically reply with the reply texts according to the reply confirmation instruction. The data query module is used to respond to the query instruction and query at least one of the customer review data, the corresponding sentiment tendency, business inspection items, statistical analysis data, comprehensive evaluation information, pushed learning tasks, and previous store inspection evaluation data of each store.

[0075] Example: A certain store received a review, the content of which is: "What... where is my spoon? Where is my receipt? What's the deal with giving a transparent rice spoon? I didn't notice until I got home that my portion is different from what I usually eat. Fortunately, the one I bought for my friend is the normal configuration. But this big spoon of mine... really ruins the mood!! There's no atmosphere at all. Deduction of salary!!!". After sentiment analysis, the customer's sentiment is negative; it is recommended that the merchant reply with the following content: Dear customer, we are very sorry for bringing you such a bad shopping experience. We attach great importance to the problems you feedback. The cold and lack of enthusiasm of the service staff is a serious dereliction of our management. We sincerely apologize to you again and hope to have the opportunity to make up for this mistake in the future. The associated business inspection items are: Service quality → Attitude of the service staff - The service staff should treat customers warmly, politely, and patiently, and provide considerate service; Customer experience → The store atmosphere is comfortable (temperature, music, lighting). The extracted words can be: receipt, spoon, atmosphere, etc.

[0076] It can be seen that the store management system provided in this embodiment can collect customer review data of each store by using the data collection module; use the data analysis module to determine the sentiment tendency of the customer review data of each store and the associated business inspection items, and statistically analyze the customer review data of each store to obtain corresponding statistical analysis data; use the data integration module to generate comprehensive evaluation information for the corresponding store based on the sentiment tendency, business inspection items, and statistical analysis data of each store; use the data recommendation module to determine the stores that need to recommend learning tasks and the stores that need to be inspected based on the sentiment tendency, business inspection items, and statistical analysis data of each store. Thus, based on the customer review data of each store, from data collection to analysis, processing, integration, and recommendation, a closed-loop processing of data is achieved, and finally, the stores that need to recommend learning tasks and the stores that need to be inspected are automatically determined, providing necessary data support for store inspections; the store patrol personnel can achieve targeted management for the stores that need to recommend learning tasks and the stores that need to be inspected, reducing the store management difficulty and management workload.

[0077] In one example, a store management method may include the following steps:

[0078] Step 101: Obtain review data and complete the mapping relationship with the store management system.

[0079] Obtain the customer review data of the store through RPA technology or API interface method. And associate the customer review data of the same target store with the store identifier in the store management system.

[0080] Step 102: Analyze the customer evaluation data using a large model, specifically including:

[0081] Use an AI large model to analyze the sentiment tendency of the review content, and it is: positive, neutral, or negative; specifically, transmit the review data to the sentiment analysis model to analyze the customer's sentiment (positive / neutral / negative), and analyze the relationship between the review score and the customer's actual sentiment.

[0082] Use another AI large model to analyze the review content and match and associate it with the enterprise's business inspection items; specifically, after processing the review data and the enterprise's inspection items through prompt engineering, submit them to the large model (which can be a general large model), and the large model analyzes the review content and the inspection items, and associates the matching inspection items (i.e., business inspection items) with the review content to prepare for subsequent business processes and inspection item analysis.

[0083] Use a third AI large model to give merchant reply suggestions based on the review content; specifically, after processing the review content through prompt engineering, it is transmitted to the merchant reply model (i.e., the content generation model), and reasonable and friendly merchant reply suggestions are generated by analyzing the review content. Users can set automatic or manual intelligent reply to review data.

[0084] It is also possible to count the high-frequency words in the reviews to form a word cloud. For example: after parsing the text, extract the dish names and word frequencies to correct the incorrect dish names in the customer reviews.

[0085] Step 103, use the review data and the corresponding analysis results for store management.

[0086] If a negative review from a customer is received and a check item is matched, training tasks (the training materials come from the check item configuration) and to-do list rectification tasks can be automatically sent to the corresponding store.

[0087] It is possible to analyze the number of new reviews, the number of negative reviews, the negative review rate, the month-on-month comparison, and the details of each channel within a cycle for each store; and provide high-frequency word clouds, as well as data such as the number of negative reviews and the negative review rate corresponding to the check items. When store supervisors and other personnel conduct store inspections, they can see the stores that need to be focused on and assisted recommended by the system based on comprehensive factors such as review scores and store inspection scores. When store inspectors check whether a certain check item in a store is qualified, in addition to looking at the current situation of the store, they can also retrieve the customer review data related to this check item, and can more truly understand whether the store meets the requirements. If there is customer review data for a check item or store inspection labels such as unqualified last time during a store inspection, directly click to view the details. For specific details, please refer to Figure 7 。

[0088] According to this embodiment, the following can be achieved:

[0089] 1. Efficient information transmission and personalized service: By integrating customer review content from various channels, instant push of review information is realized, and customer feedback can be obtained in a timely manner. At the same time, the system provides personalized reply suggestions, avoiding monotony and perfunctoriness in merchant replies.

[0090] 2. Real-time problem warning and precise rectification: When a customer's review is negative, the system automatically sends learning tasks and rectification to-do lists to store personnel, enabling the store to discover and rectify problems in a timely manner without waiting until monthly or quarterly summary and review, greatly improving the timeliness of problem solving.

[0091] 3. Decision-making data support: Comprehensive and in-depth store review data is provided, including key indicators such as the change trend of review scores and the new negative review rate. At the same time, the system also provides data such as word frequency analysis and the negative review rate related to check items, which can help the corresponding staff quickly understand the business status, reduce the time for report making, and provide a clear direction for the management focus in the next stage.

[0092] 4. Convenient store visit support: It provides highly integrated information support for store visits, allowing direct query of store review scores, keywords, and other information. During the store visit process, the system can also query in real time the review content related to the current inspection item, helping store visit personnel more accurately assess and assist stores, and improving the efficiency and effectiveness of store visits.

[0093] 5. Intelligent store assistance recommendation: Combining data such as store visit situations and customer evaluations, the system can comprehensively analyze and recommend stores that require key attention and assistance. This intelligent recommendation mechanism helps management quickly locate problem stores.

[0094] It can be seen that this embodiment provides personalized services and intelligent decision-making support by integrating multi-platform data.

[0095] Next, another store management method provided by the embodiments of the present application will be introduced. The store management method described below can be referred to mutually with the solutions described in other embodiments.

[0096] The embodiments of the present application disclose a store management method, including: collecting customer review data of each store; determining the sentiment tendency and associated business inspection items of the customer review data of each store, and statistically analyzing the customer review data of each store to obtain corresponding statistical analysis data; generating comprehensive evaluation information of the corresponding store based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store; determining the stores that need to recommend learning tasks and the stores that need to be inspected based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store.

[0097] In one implementation, collecting customer review data of each store includes: exporting user evaluation information of each store from at least one channel; cleaning the exported user evaluation information, unifying the data format, and then mapping the user evaluation information to the store identifiers set in the current system to obtain the customer review data of each store.

[0098] In one implementation, determining the sentiment tendency and associated business inspection items of the customer review data of each store, and statistically analyzing the customer review data of each store to obtain corresponding statistical analysis data includes: using a sentiment analysis model to process the customer review data of each store respectively to obtain the sentiment tendency of the corresponding store; using a content analysis model to process the customer review data of each store respectively to obtain the business inspection items associated with the corresponding store; statistically analyzing the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information of the customer review data of each store, and simultaneously statistically analyzing the high-frequency words, misused words, number of reviews, number of negative reviews, negative review rate, and month-on-month information by channel to obtain corresponding statistical analysis data.

[0099] In one embodiment, it further includes: using a content generation model to generate corresponding response texts for the customer review data of each store, and automatically replying with the response texts according to the reply confirmation instruction.

[0100] In one embodiment, based on the sentiment tendency, business inspection items, and statistical analysis data corresponding to each store, comprehensive evaluation information for the corresponding store is generated, including: statistically presenting the sentiment tendency, business inspection items, statistical analysis data, and past store visit evaluation data corresponding to each store in the form of a chart; using the corresponding chart statistical result as the comprehensive evaluation information for the corresponding store.

[0101] In one embodiment, it further includes: pushing corresponding learning tasks to the stores that need to be recommended for learning tasks; marking inspection prompt information for the stores that need to be inspected; the inspection prompt information includes at least one of the following: the business inspection items corresponding to the store to be inspected, the customer review data associated with the business inspection item, and the past store visit evaluation data corresponding to the store to be inspected. In response to a query instruction, at least one of the customer review data, corresponding sentiment tendency, business inspection items, statistical analysis data, comprehensive evaluation information, pushed learning tasks, and past store visit evaluation data of each store is queried.

[0102] It can be seen that this application is based on the customer review data of each store, and realizes the closed-loop processing of data from data collection to analysis, processing, integration, and recommendation. Finally, the stores that need to be recommended for learning tasks and the stores that need to be inspected are automatically determined, providing necessary data support for store inspections; the store visit personnel can manage the stores that need to be recommended for learning tasks and the stores that need to be inspected in a targeted manner, reducing the difficulty and workload of store management. The so-called closed-loop processing of data can also refer to Figure 8 , Figure 8 The intelligent platform in is the store management system.

[0103] Next, an electronic device provided by an embodiment of this application is introduced. The electronic device described below can be referred to in mutual reference with the store management method and device described above.

[0104] An embodiment of this application discloses an electronic device, including:

[0105] A memory for storing a computer program;

[0106] A processor for executing the computer program to implement the method disclosed in any of the above embodiments.

[0107] Next, a readable storage medium provided by an embodiment of this application is introduced. The readable storage medium described below can be referred to in mutual reference with the store management method, device, and equipment described above.

[0108] A readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, it implements the store management method disclosed in the foregoing embodiments. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated herein.

[0109] Next, a computer program product provided by an embodiment of the present application will be introduced. The computer program product described below may be mutually referred to with other embodiments described herein.

[0110] A computer program product includes a computer program / instructions, and when the computer program / instructions are executed by a processor, it implements the steps of the store management method disclosed above.

[0111] The "first", "second", "third", "fourth", etc. (if any) involved in the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, or devices.

[0112] It should be noted that the descriptions involving "first", "second", etc. in the present application are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0113] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0114] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be implemented directly in hardware, in software modules executed by a processor, or in a combination thereof. The software modules may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of readable storage medium known in the art.

[0115] Specific examples are used in this article to illustrate the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. At the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A store management system, characterized in that: include: Data collection module, used to collect customer review data of each store; The data analysis module is used to determine the sentiment tendency of the customer review data of each store and the associated business inspection items, and statistically analyze the customer review data of each store to obtain corresponding statistical analysis data; The data integration module is used to generate comprehensive evaluation information of the corresponding stores based on the sentiment tendency, business inspection items and statistical analysis data of each store; The data recommendation module is used to determine the stores that need to be recommended learning tasks and the stores that need to be inspected based on the sentiment tendencies, business inspection items and statistical analysis data corresponding to each store.

2. The system according to claim 1, characterized in that The data collection module is used to: Export user evaluation information of each store from at least one channel; After the exported user evaluation information is cleaned and the data format is unified, the user evaluation information is mapped to the store identifiers set by the current system to obtain the customer review data of each store.

3. The system according to claim 1, characterized in that The data analysis module is used for: Use sentiment analysis models to process customer review data of each store and obtain the sentiment tendency of the corresponding store; Use the content analysis model to process the customer review data of each store and obtain the business inspection items associated with the corresponding store; Statistical analysis is performed on the high-frequency words, incorrect words, number of comments, number of negative reviews, negative review rate, and month-on-month information of customer review data for each store. At the same time, statistics are performed on the high-frequency words, incorrect words, number of comments, number of negative reviews, negative review rate, and month-on-month information by channel to obtain corresponding statistical analysis data.

4. The system according to claim 1, characterized in that Also includes: The intelligent reply module is used to use the content generation model to generate corresponding reply texts for the customer review data of each store, and automatically reply with the reply text according to the reply confirmation instruction.

5. The system according to claim 1, characterized in that The data integration module is used to: The emotional tendencies, business inspection items, statistical analysis data and previous store inspection evaluation data of each store are statistically analyzed in the form of charts; The corresponding chart statistical results are used as the comprehensive evaluation information of the corresponding store.

6. The system according to claim 1, characterized in that The data recommendation module is used to: Push corresponding learning tasks to stores that need recommended learning tasks; Mark inspection prompt information for the store that needs to be inspected; the inspection prompt information includes at least one of the following: the business inspection item corresponding to the store that needs to be inspected, the customer review data associated with the business inspection item, and the previous store inspection evaluation data corresponding to the store that needs to be inspected.

7. The system according to any one of claims 1 to 6, characterized in that: Also includes: The data query module is used to respond to the query instruction and query at least one of the customer review data of each store, the corresponding emotional tendency, the business inspection items, the statistical analysis data, the comprehensive evaluation information, the pushed learning tasks and the previous store inspection evaluation data.

8. A store management method, characterized in that: include: Collect customer review data for each store; Determine the sentiment tendency of customer review data of each store and the associated business inspection items, and statistically analyze the customer review data of each store to obtain corresponding statistical analysis data; Generate comprehensive evaluation information of the corresponding stores based on the sentiment tendency, business inspection items and statistical analysis data of each store; Based on the sentiment tendencies, business inspection items and statistical analysis data corresponding to each store, determine the stores that need to be recommended learning tasks and the stores that need to be inspected.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the method according to claim 8.

10. A readable storage medium, characterized in that: Used to store a computer program, wherein the computer program implements the method according to claim 8 when executed by a processor.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method of claim 8 is implemented.

Images