Method, device, server, storage medium and program product for data analysis

Abstract

The application provides a data analysis method, device, server, storage medium and program product, relates to the technical field of computers, and the method comprises the following steps: acquiring first data corresponding to a target business index of a target store in a first business cycle, second data corresponding to the target business index of the target store in a second business cycle, and third data corresponding to the target business index of the target store in a specified time range, wherein the target business index comprises one or more of sales, average single price, visitor number, order number and conversion rate, and the specified time range comprises N business cycles, and N is an integer greater than 2; determining an abnormal change threshold corresponding to the target business index based on the third data corresponding to the target business index of the target store in the specified time range; and determining whether the target business index is abnormal based on the first data, the second data and the abnormal change threshold. The application can provide the analysis efficiency of business data.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data analysis method, apparatus, server, storage medium, and program product. Background Technology

[0002] With the development of e-commerce technology, more and more stores are joining e-commerce platforms. During their operation on these platforms, stores generate operational data, including various business metrics such as sales volume, order volume, visitor count, conversion rate, and average order value.

[0003] To understand the performance of their stores, merchants need to compile historical operating data themselves and then manually analyze it to check for any abnormal changes in business indicators such as sales volume, order volume, number of visitors, conversion rate, and average order value. However, manual analysis requires a lot of time and energy from merchants and is very inefficient. Summary of the Invention

[0004] This application provides a data analysis method, apparatus, server, storage medium, and program product, which can improve the efficiency of business data analysis. The technical solution is as follows: Firstly, a data analysis method is provided, the method comprising: The system obtains first data corresponding to the target business indicators of the target store in the first operating cycle, second data corresponding to the target business indicators of the target store in the second operating cycle, and third data corresponding to the target business indicators of the target store within a specified time range. The target business indicators include one or more of the following: sales revenue, average order value, number of visitors, number of orders, and conversion rate. Based on the third data corresponding to the target business indicators of the target store within a specified time range, an abnormal change threshold corresponding to the target business indicators is determined, wherein the specified time range includes N operating cycles, and N is an integer greater than 2; Based on the first data, the second data, and the abnormal change threshold, it is determined whether the target business indicator is abnormal.

[0005] In one possible implementation, determining the abnormal change threshold corresponding to the target business indicator based on third data corresponding to the target business indicator within a specified time range for the target store includes: For the data corresponding to the target business indicators in each of the N operating cycles, calculate the month-on-month change rate of the target business indicators in the two adjacent operating cycles. Based on the month-on-month change rate of the target business indicator within the two adjacent operating cycles, a month-on-month change rate threshold corresponding to the target business indicator is determined, which is used as the abnormal change threshold.

[0006] In one possible implementation, determining the abnormal change threshold corresponding to the target business indicator based on third data corresponding to the target business indicator within a specified time range for the target store includes: If the operating cycle of the target store within the specified time range is N, then based on the third data corresponding to the target business indicator of the target store within the specified time range, the abnormal change threshold corresponding to the target business indicator is determined.

[0007] In one possible implementation, the method further includes: If the operating cycle of the target store within the specified time range is less than N, then based on the fourth data corresponding to the target business indicator of the similar stores corresponding to the target store within the specified time range, the month-on-month change rate threshold corresponding to the target business indicator is determined, wherein the similar stores are stores of the same type as the target store and whose store size meets the similarity condition.

[0008] In one possible implementation, the method further includes; Based on whether the target business indicators are abnormal, an operational analysis report for the target store is generated using a pre-trained Large Language Model (LLM). The operational analysis report is used to indicate the operational status of the target store and optimization strategies for the operational status.

[0009] In one possible implementation, the step of generating an operational analysis report for the target store based on whether the target business metrics are abnormal, using a pre-trained LLM, includes: Based on whether the target business indicators are abnormal, RAG is generated through enhanced retrieval, and business optimization strategies are retrieved. Based on the first data, the second data, and the business optimization strategy, an business analysis report for the target store is generated using LLM.

[0010] In one possible implementation, the step of generating a Reliable Area Code (RAG) based on whether the target business metrics are abnormal, and retrieving operational optimization strategies, includes: If the target business indicator is abnormal, perform root cause analysis on the target business indicator to obtain the root cause indicator of the abnormality, and retrieve the business optimization strategy associated with the root cause indicator through RAG. If the target business metrics are not abnormal, then the RAG is used to retrieve operational optimization strategies associated with increasing sales.

[0011] In one possible implementation, the business analysis report includes at least one optimization suggestion generated based on the business optimization strategy, wherein each optimization suggestion corresponds to source information and confidence level.

[0012] In one possible implementation, the method further includes: If the optimization suggestions included in the business analysis indicate that the target plugin should be optimized, the optimization suggestions for the target plugin will be displayed on the terminal. In response to the confirmation of the optimization suggestions for the target plugin, the configuration of the target plugin is updated according to the optimization suggestions.

[0013] Secondly, a data analysis apparatus is provided, characterized in that the apparatus comprises: The acquisition module is used to acquire first data corresponding to the target business indicators of the target store in the first operating cycle, second data corresponding to the target business indicators of the target store in the second operating cycle, and third data corresponding to the target business indicators of the target store within a specified time range. The target business indicators include one or more of the following: sales revenue, average order value, number of visitors, number of orders, and conversion rate. The analysis module is used to determine the abnormal change threshold corresponding to the target business indicator based on the third data corresponding to the target business indicator of the target store within a specified time range, wherein the specified time range includes N operating cycles, and N is an integer greater than 2; and to determine whether there is an anomaly in the target business indicator based on the first data, the second data and the abnormal change threshold.

[0014] In one possible implementation, the analysis module is used for: For the data corresponding to the target business indicators in each of the N operating cycles, calculate the month-on-month change rate of the target business indicators in the two adjacent operating cycles. Based on the month-on-month change rate of the target business indicator within the two adjacent operating cycles, a month-on-month change rate threshold corresponding to the target business indicator is determined, which is used as the abnormal change threshold.

[0015] In one possible implementation, the analysis module is used for: If the operating cycle of the target store within the specified time range is N, then based on the third data corresponding to the target business indicator of the target store within the specified time range, the month-on-month change rate threshold corresponding to the target business indicator is determined.

[0016] In one possible implementation, the analysis module is used for: If the operating cycle of the target store within the specified time range is less than N, then based on the fourth data corresponding to the target business indicator of similar stores within the specified time range, a month-on-month change rate threshold corresponding to the target business indicator is determined. Here, the similar stores are those of the same type as the target store and whose store size meets the similarity criteria.

[0017] In one possible implementation, the analysis module is further configured to: Based on whether the target business indicators are abnormal, an operational analysis report for the target store is generated using a pre-trained Large Language Model (LLM). The operational analysis report is used to indicate the operational status of the target store and optimization strategies for the operational status.

[0018] In one possible implementation, the analysis module is used for: Based on whether the target business indicators are abnormal, RAG is generated through enhanced retrieval, and business optimization strategies are retrieved. Based on the first data, the second data, and the business optimization strategy, an business analysis report for the target store is generated using LLM.

[0019] In one possible implementation, the analysis module is used for: If the target business indicator is abnormal, perform root cause analysis on the target business indicator to obtain the root cause indicator of the abnormality, and retrieve the business optimization strategy associated with the root cause indicator through RAG. If the target business metrics are not abnormal, then the RAG is used to retrieve operational optimization strategies associated with increasing sales.

[0020] In one possible implementation, the business analysis report includes at least one optimization suggestion generated based on the business optimization strategy, wherein each optimization suggestion corresponds to source information and confidence level.

[0021] In one possible implementation, the apparatus further includes an execution module for: If the optimization suggestions included in the business analysis indicate that the target plugin should be optimized, the optimization suggestions for the target plugin will be displayed on the terminal. In response to the confirmation of the optimization suggestions for the target plugin, the configuration of the target plugin is updated according to the optimization suggestions.

[0022] Thirdly, a server is provided, the server including a processor and a memory, the memory storing at least one instruction, the instruction being loaded and executed by the processor to perform the operations performed as described in the first aspect above and any possible method of data analysis described in the first aspect.

[0023] Fourthly, a computer-readable storage medium is provided, the storage medium storing at least one instruction that is loaded and executed by a processor to perform the operations performed by the first aspect and any possible method of data analysis described in the first aspect.

[0024] Fifthly, a computer program product is provided, the computer program product storing at least one instruction, the instruction being loaded and executed by a processor to perform the operations performed as described in the first aspect and any possible implementation of the data analysis method described in the first aspect.

[0025] The beneficial effects of the technical solution provided in this application are: In the technical solution provided in this application, an abnormal change threshold corresponding to the target business indicator is dynamically generated based on the data corresponding to the target business indicator of the target store within a specified time range. Then, based on the abnormal change threshold, the first data corresponding to the target business indicator of the target store in the first operating cycle and the second data corresponding to the target business indicator in the second operating cycle are analyzed to determine whether there is an abnormality in the target business indicator. Compared with manual analysis, this method is more efficient. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a data analysis method provided in an embodiment of this application; Figure 2 This is a flowchart of a data analysis method provided in an embodiment of this application; Figure 3 This is a flowchart of a data analysis method provided in an embodiment of this application; Figure 4 This is a schematic diagram of a data analysis device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 6This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0029] With the development of e-commerce technology, more and more stores are joining e-commerce platforms. During their operation on these platforms, stores generate a large amount of operational data related to sales, traffic, orders, and user behavior, such as sales revenue, order volume, visitor count, conversion rate, and average order value. To enable merchants to understand their store's performance, e-commerce platforms display this data to them through their backend systems. Merchants then manually analyze this data to determine their business situation. However, manual analysis is time-consuming and inefficient.

[0030] This application provides a data analysis method that can be implemented by a server, which can be a backend server of an e-commerce platform. The backend server can be a single server or a server cluster. In this method, based on the data corresponding to target business indicators of a target store within a specified time range, an abnormal change threshold corresponding to the target business indicator is dynamically generated. Then, based on this abnormal change threshold, the first data corresponding to the target business indicator in the first operating cycle and the second data corresponding to the target business indicator in the second operating cycle are analyzed to determine whether there are any abnormalities in the target business indicator. This method is more efficient than manual analysis.

[0031] The data analysis method provided in the embodiments of this application will be described below with reference to the accompanying drawings. This method can be implemented by a server, such as... Figure 1 As shown, the method may include the following processing steps: Step 101: Obtain the first data corresponding to the target business indicators of the target store in the first operating cycle, the second data corresponding to the target business indicators of the target store in the second operating cycle, and the third data corresponding to the target business indicators of the target store within a specified time range.

[0032] If a merchant needs to understand the operational status of their store, they can enter relevant text through a smart customer service page provided on the e-commerce platform's client application using a terminal device. The terminal then sends the text to the server, which determines whether the merchant requires operational analysis of the target store based on the text. If so, the server executes the data analysis method provided in this embodiment to perform operational data analysis.

[0033] There can be multiple methods for making this judgment; two of them are illustrated below.

[0034] Method 1: Keyword Matching The server can be pre-configured with keywords corresponding to business analysis needs, such as business analysis, store analysis, business performance, data analysis, and sales analysis. After receiving the above text, the server extracts the keywords from the text and matches them with the pre-configured keywords corresponding to business analysis needs. If a matching keyword is found, it is determined that the merchant has a need for business analysis of the target store.

[0035] Method 2: Intent Recognition Model The server can pre-deploy an intent recognition model, which can be a pre-trained NLP (Natural Language Processing) model. After receiving the above text, the server inputs the text into the intent recognition model, and the intent recognition model outputs the recognition result, which is used to indicate whether the merchant has a need for business analysis of the target store.

[0036] The two methods described above can be used individually or in combination. For example, method one can be used first for keyword matching; if no matching keyword is found, method two can be used for intent recognition.

[0037] After determining that the merchant has a need for operational analysis of the target store, proceed with step 101 above.

[0038] In step 101 above, the server uses the current date as a base and performs a sliding calculation based on natural days to determine the first and second operating cycles. Each operating cycle consists of M natural days, where M can be 7. Let the current date be denoted as T. Then the first operating cycle is (T-7, T-1), and the second operating cycle is (T-14, TT-8). That is, the time range of the first operating cycle is from 7 days ago to yesterday, and the time range of the second operating cycle is from 14 days ago to 8 days ago.

[0039] For example, if the current date T is 2026-07-11, then the first operating cycle is from 2026-07-04 to 2026-07-10, and the second operating cycle is from 2026-06-27 to 2026-07-03.

[0040] After determining the first operating cycle and the second operating cycle, we can further obtain the first data corresponding to the target business indicators of the target store in the first operating cycle, and the second data corresponding to the target business indicators of the target store in the second operating cycle.

[0041] The target business metrics may include, but are not limited to, one or more of the following: sales revenue, number of orders, number of visitors, number of users placing orders, average order value, and conversion rate. Data on sales revenue, number of orders, number of visitors, number of users placing orders, and number of visitors can be obtained directly from the database. Average order value can be obtained by dividing sales revenue by the number of orders, and conversion rate can be obtained by dividing the number of users placing orders by the number of visitors.

[0042] The first set of data may include summary data, daily data, and individual product data for the target store's target business metrics within the first operating period. The summary data includes the sum of sales revenue, order count, visitor count, and number of users placing orders within the first operating period, as well as the average order value calculated from the sum of sales revenue and order count, and the conversion rate calculated from the sum of users placing orders and visitor count. The daily data includes the sales revenue, order count, visitor count, and number of users placing orders for each day within the first operating period, as well as the daily average order value calculated from the daily sales revenue and order count, and the daily conversion rate calculated from the daily number of users placing orders and visitor count. The individual product data includes the sales revenue, order count, visitor count, and number of users placing orders for each product within the first operating period, as well as the average order value calculated from the sales revenue and order count for each product, and the conversion rate calculated from the number of users placing orders and visitor count for each product.

[0043] Daily data includes daily sales, number of orders, number of visitors, number of users placing orders, and the daily average order value calculated based on daily sales and order volume, as well as the daily conversion rate calculated based on the daily number of users placing orders and visitors. Individual product data includes sales, number of orders, number of visitors, number of users placing orders, and the average order value calculated for each product, as well as the conversion rate calculated for each product, based on the number of users placing orders and visitors.

[0044] In addition to the first and second data mentioned above, in order to calculate the dynamic threshold used to determine whether the target business indicator is normal, data corresponding to the target business indicator over a larger time range can also be obtained. Specifically, the processing can be as follows: The server can obtain third-party data corresponding to the target business indicators of the target store within a specified time range. The specified time range can include N consecutive operating cycles, which include the first and second operating cycles mentioned above.

[0045] The third data corresponding to the target business indicators of the target store within a specified time range includes the summary data of the target business indicators of the target store in each operating cycle within the specified time range.

[0046] The specified time range includes N operating cycles, where N is an integer greater than 2. The value of N can be configured by relevant personnel according to actual needs, for example, N=8, 12, etc.

[0047] Step 102: Based on the third data corresponding to the target business indicators of the target store within a specified time range, determine the threshold for abnormal changes in the target business indicators.

[0048] After obtaining the third-party data corresponding to the target business indicators of the target store within a specified time range, the server calculates the month-on-month change rate of the target business indicator for each target business indicator, for the aggregated data of every two adjacent operating cycles out of N operating cycles. This yields N-1 month-on-month change rates for the target business indicator. Furthermore, based on these N-1 month-on-month change rates, a threshold for the month-on-month change rate corresponding to the target business indicator is determined as the abnormal change threshold. Specifically, the processing can be as follows: For each target business indicator, calculate the average of N-1 month-on-month change rates corresponding to that target business indicator, and determine the month-on-month change rate threshold for that target business indicator based on the average value. There can be multiple methods for determining this threshold; several examples are listed below for illustration.

[0049] Method 1: Use the absolute value of the average as the threshold for the month-on-month change rate of the target business indicator.

[0050] Method 2: Calculate the standard deviation, denoted as σ, based on the mean, and then compare it with the default threshold and k. The larger of the two values, σ and k, is used as the month-on-month change rate threshold for the target business indicator. k is a constant coefficient that can be pre-configured, for example, k=2. The default threshold can also be pre-configured, and different target business indicators can have different default thresholds.

[0051] For example, if the target business metric is conversion rate, N=13, and the conversion rates over 13 operating cycles are [4.5%, 4.4%, 4.6%, 4.3%, 4.5%, 4.2%, 4.0%, 4.1%, 4.3%, 4.2%, 4.4%, 4.3%, 4.6%], then the month-on-month change rate of conversion rates between adjacent operating cycles is calculated as [-2.22%, 4.55%, -6.52%, 4.65%, -6.67%, -4.76%, 2.50%, 4.88%, -2.33%, 4.76%, -2.27%, 6.98%]. Furthermore, the standard deviation σ of these 12 month-on-month change rates is 4.47%. Then, the default threshold and k are compared. The magnitude of σ is used as the threshold for the month-on-month change in conversion rate. As shown in the formula below: max(10%, 2 × 4.47%) = max(10%, 8.94%) = 10% Where k=2, the default threshold is 10%, and max() means taking the maximum value.

[0052] In addition, if a major promotional event occurs within the specified time frame, the data for the target business metrics on the target date of the promotional event will be corrected, and the modified data will be used to determine the month-on-month change rate threshold for the target business metrics.

[0053] Specifically, you can replace the target business metric's data on the target date with the data from the target corresponding day of the target date. The target corresponding day of the target date can be the nearest corresponding day without a major promotional event. A corresponding day refers to the same position within two weeks; for example, this week's Monday and last week's Monday are corresponding days.

[0054] After obtaining the threshold for abnormal changes corresponding to the target business metric, the anomaly detection conditions for that target business metric can be further determined. Specifically, the anomaly detection conditions can be as follows: If the absolute value of the month-on-month change rate of the target business indicator calculated based on the first and second data is less than the abnormal change threshold of the target business indicator, then it is determined that the target business indicator is not abnormal; if the absolute value of the month-on-month change rate of the target business indicator calculated based on the first and second data is greater than or equal to the abnormal change threshold of the target business indicator, then it is determined that the target business indicator is abnormal.

[0055] In one possible implementation, if the target store is new and has a short operating history, the month-on-month change rate threshold for the target business indicator can be determined based on the fourth data point corresponding to the target business indicator from similar stores within a specified time range. Specifically, the process can be as follows: If the operating cycle of the target store within the specified time range is less than N, then the similar stores corresponding to the target store are identified, and the fourth data corresponding to the target business indicators of the similar stores within the specified time range is obtained. Then, based on the fourth data, the month-on-month change rate threshold corresponding to the target business indicators is determined. Here, the similar stores are stores with the same store type as the target store and whose store size meets the similarity condition. The similarity condition can be that the store size similarity is greater than the threshold. The threshold can be configured according to actual needs, for example, the threshold is 95%.

[0056] The process of determining the month-on-month change rate threshold corresponding to the target business indicator based on the fourth data is the same as that of determining the month-on-month change rate threshold corresponding to the target business indicator based on the third data, and will not be repeated here.

[0057] Step 103: Based on the first data, the second data, and the abnormal change threshold, determine whether there are any abnormalities in the target business indicators.

[0058] After obtaining the first and second data mentioned above, the month-on-month change rate of the target business indicators in the first operating period compared to the second operating period can be calculated using the sum of the target business indicators included in the first data and the sum of the target business indicators included in the second data.

[0059] If the absolute value of the month-on-month change rate is less than the abnormal change threshold corresponding to the target business indicator, then the target business indicator is determined to be normal; if the absolute value of the month-on-month change rate is greater than or equal to the abnormal change threshold corresponding to the target business indicator, then the target business indicator is determined to be abnormal.

[0060] In one possible implementation, in order to eliminate the week-of-week effect, a comparative method can be used to correct the year-on-year change rate of the first operating cycle compared to the second operating cycle. Specifically, there are several correction methods, one of which is illustrated below.

[0061] The first and second operating cycles each consist of 7 calendar days. Each calendar day in the first operating cycle corresponds to a corresponding day in the second operating cycle. For example, Monday in the first operating cycle and Monday in the second operating cycle are a pair of corresponding days, and Saturday in the first operating cycle and Saturday in the second operating cycle are a pair of corresponding days. For each pair of corresponding days in the first and second operating cycles, the month-on-month change rate of the target business indicator is calculated for that pair of corresponding days. In this way, the month-on-month change rates of the target business indicator for each of the 7 pairs of corresponding days can be obtained. The median of these 7 month-on-month change rates is taken as the adjusted month-on-month change rate of the target business indicator in the first operating cycle compared to the second operating cycle.

[0062] After calculating the revised month-on-month change rate of the target business indicators for the first operating period compared to the second operating period, the revised month-on-month change rate of the target business indicators can be compared with the magnitude of the corresponding month-on-month change rate threshold.

[0063] If both the original and revised month-on-month change rates of the target business indicator are greater than the corresponding month-on-month change rate threshold, then the target business indicator is determined to be abnormal; otherwise, the target business indicator is determined to be normal.

[0064] In one possible implementation, if an anomaly is identified in the target business metric, root cause analysis can be performed to determine the root cause metric. Specifically, the process can be as follows: If an anomalies are identified in the target business metrics, these metrics are broken down based on their product relationships. Taking sales revenue as an example, sales revenue = number of visitors × conversion rate × average order value. The contribution of each of these three metrics—number of visitors, conversion rate, and average order value—to changes in sales revenue is quantified and ranked according to their contribution. The metric with the largest contribution is then identified as the root cause metric. After determining the root cause metric, the Y target products with the largest absolute values ​​of the month-on-month change rate corresponding to the root cause metric in the first and second operating cycles can be further identified. Y can be configured according to actual needs; for example, Y=2.

[0065] The contribution rate can be calculated using logarithmic decomposition, which breaks down the logarithmic change in sales revenue into the sum of the logarithmic changes in three business indicators. The specific calculation formula is as follows: ln(Sales revenue in the first operating period / Sales revenue in the second operating period) = ln(Number of visitors in the first operating period / Number of visitors in the second operating period) + ln(Conversion rate in the first operating period / Conversion rate in the second operating period) + ln(Average order value in the first operating period / Average order value in the second operating period).

[0066] For each business metric, the logarithmic change in that metric is taken as its contribution value. The sign of the contribution value indicates the direction of the metric's impact on sales revenue; a positive value indicates an increase in sales revenue, and a negative value indicates a decrease. For example, the logarithmic change in visitor count is ln(visitor count in the first operating period / visitor count in the second operating period), the logarithmic change in conversion rate is ln(conversion rate in the first operating period / conversion rate in the second operating period), and the logarithmic change in average order value is ln(conversion rate in the first operating period / conversion rate in the second operating period).

[0067] Furthermore, the absolute value of each business indicator's contribution, as a percentage of the sum of the absolute values ​​of the three business indicators' contributions, is taken as the contribution of that business indicator to changes in sales revenue.

[0068] For example, in the second operating cycle, the target store had 10,000 visitors, a conversion rate of 4.0%, and an average order value of 200 yuan, resulting in sales of 10,000 × 4.0% × 200 = 80,000 yuan. In the first operating cycle, the store had 8,000 visitors, a conversion rate of 4.4%, and an average order value of 205 yuan, resulting in sales of 8,000 × 4.4% × 205 = 72,160 yuan, a decrease of 9.8% compared to the previous cycle. The contribution values ​​of the three business indicators are as follows: the contribution value of the number of visitors is ln(8,000 / 10,000) = -0.2231, the contribution value of the conversion rate is ln(4.4% / 4.0%) = 0.0953, and the contribution value of the average order value is ln(205 / 200) = 0.0247. The sum of the three is -0.1031, which equals ln(72,160 / 80,000), so the decomposition is valid. The sum of the absolute values ​​of the contributions of the three business metrics is 0.2231 + 0.0953 + 0.0247 = 0.3431. Therefore, the contribution of visitor count is 0.2231 / 0.3431 = 65.0%, the contribution of conversion rate is 0.0953 / 0.3431 = 27.8%, and the contribution of average order value is 0.0247 / 0.3431 = 7.2%. Ranked by contribution, visitor count has the largest contribution, and its negative value indicates that the decline in sales was mainly caused by a decrease in visitor count. Therefore, visitor count is identified as the root cause metric.

[0069] If the root cause metric is visitor count, then you can further identify the target channel causing the abnormal visitor count across multiple channels. Here, "channel" refers to the way users access the store. These channels can include organic search, paid advertising, social media, direct visits, and so on.

[0070] In one possible implementation, the technical solution provided in this application embodiment can also generate an operational analysis report for the target store based on whether there are anomalies in the target business indicators, using a pre-trained LLM. The operational analysis report is used to indicate the store's operational status and optimization strategies based on that status.

[0071] If the target business metrics are abnormal, then... Figure 2As shown, using RAG (Related Aspects of Interest), a composite search key is constructed using three factors: root cause indicators, month-on-month change direction (positive month-on-month change rate indicates an upward trend, negative month-on-month change rate indicates a downward trend), and the industry category of the target store. This search is performed in the knowledge base, yielding at least one result. Then, based on the relevance and confidence of each search result with the composite search key, a comprehensive ranking is performed. The top X search results are selected as the business optimization strategy. This comprehensive ranking can refer to adding the relevance of the search results with the composite search key and the confidence of the search results (or weighting them according to specified weights) to obtain a comprehensive score for the search results, and then selecting the X search results with the highest comprehensive scores.

[0072] If there are no anomalies in the target business metrics, then use RAG to retrieve at least one search result that is associated with increasing sales, as an operational optimization strategy.

[0073] After retrieving the operational optimization strategy, the target store's data evidence and the retrieved operational optimization strategy are input into the prompt word template to generate prompt words. These prompt words constrain the LLM to only analyze the possible causes of abnormal root cause indicators based on the retrieved operational optimization strategy and data evidence, and generate at least one optimization suggestion, prohibiting arbitrary suggestions. The data evidence may include the month-on-month change rate of each target business indicator for the target store in the first and second operating cycles, root cause indicators, and information on the Y target products for which the absolute value of the month-on-month change rate of the root cause indicator for the target store is the largest in the first and second operating cycles.

[0074] Furthermore, such as Figure 3 As shown, the aforementioned prompts are input into the LLM (Local Management Module), which outputs at least one optimization suggestion. Each suggestion includes a link to the source document and a confidence score, forming the optimization suggestion text. Then, based on the aforementioned data evidence, a business summary text is generated. This can be generated using the LLM or a preset template; this embodiment does not impose any limitations on this.

[0075] For example, a business summary document could look like this: "Your store's performance last week was as follows:" 1. Sales revenue increased by more than 10% month-over-month, while conversion rate and average order value decreased by more than 10% month-over-month.

[0076] 2. In terms of sales: sales revenue and order volume increased by 27% and 15% respectively compared to the previous period, while the average order value decreased by 5% and 2% respectively compared to the previous period.

[0077] 3. In terms of traffic: both visitor numbers and conversion rate decreased by 8% month-over-month. Finally, add the optimization suggestions and business summary text to the business analysis report template to obtain the business analysis report.

[0078] If no business optimization strategy is found, a pre-set general fallback text is used as the optimization suggestion text. The optimization suggestion text and the business summary text are then added to the business analysis report template to obtain the business analysis report.

[0079] In one possible implementation, to enable merchants to more efficiently resolve anomalies in target business metrics, optimization suggestions from the business analysis report can be directly mapped to executable actions. Specifically, the process can be as follows: The server can be pre-configured with a mapping table between business metrics, suggestion types, plugins, jump links to plugin configuration pages, plugin configuration fields, and parameter extraction templates for plugin configuration fields. After generating the business analysis report, based on the identified root cause metrics and the suggestion types of optimization suggestions output by the LLM, the target plugin, the jump links to the target plugin's configuration page, the target plugin's configuration field schema (which may include field name, field type, value range, etc.), and the parameter extraction templates for the plugin's configuration fields are determined from this mapping table.

[0080] For example, if the root cause metric is conversion rate and the optimization suggestion type is optimizing the product details page, then the corresponding target plugin can be found in the mapping table above as an SEO (Search Engine Optimization) plugin.

[0081] For example, if the root cause metric is the number of visitors, the optimization suggestion type is to improve paid traffic from external sites, and the corresponding target plugin found in the mapping relationship table is the advertising plugin.

[0082] For example, if the root cause metric is the number of visitors and the optimization suggestion type is to increase organic search traffic, the corresponding target plugin found in the mapping table is the SEO plugin.

[0083] For example, if the root cause metric is conversion rate and the optimization suggestion type is "recover abandoned orders," the corresponding target plugin found in the mapping relationship table is the "recover abandoned orders plugin."

[0084] For example, if the root cause metric is average order value, the optimization suggestion type is to increase cross-selling, and the corresponding target plugin found in the mapping relationship table is the bundled sales plugin.

[0085] For example, if the root cause metric is average order value and the optimization suggestion type is a discount promotion, the corresponding target plugin found in the mapping table is the promotion activity plugin.

[0086] Each record in the mapping table uses the root cause metric and optimization suggestion type as keys, and the plugin identifier, the jump link to the plugin's configuration page, the plugin's configuration fields, and the parameter extraction template of the plugin's configuration fields as values. The mapping table is pre-configured by relevant personnel and updated as plugins are added, removed, or upgraded.

[0087] After querying the mapping table above, extract the parameter values ​​of each configuration field of the target plugin from the business analysis report according to the parameter extraction template of the configuration fields, and obtain a structured configuration draft. During extraction, slots can be filled using the parameter extraction template, or the parameter values ​​can be extracted from the business analysis report using an LLM library based on the parameter extraction template.

[0088] The obtained structured configuration draft is validated according to the configuration field schema, checking field type, required fields, and value range, leaving invalid or missing fields blank or assigning default values. Simultaneously, it can determine whether the target plugin is already installed in the target store's backend, serving as the basis for deciding whether to guide installation and pre-fill configuration fields in the next step, or simply provide the parameter values ​​for the configuration fields.

[0089] In the business analysis report, target plugins, suggested configuration field parameter values, and the expected impact after configuring according to the suggested parameter values ​​can be displayed in the form of action cards to be confirmed. When multiple target plugins are identified, each target plugin corresponds to an independent action card to be confirmed. When the same plugin is hit by multiple root cause indicators, they are merged into one action card to be confirmed, listing the suggested parameter values ​​for the configuration fields corresponding to each root cause indicator. When there are multiple action cards to be confirmed, they are sorted from highest to lowest according to the contribution of the corresponding root cause indicator. By default, only the top few action cards with the highest contribution are expanded, and the rest are collapsed to avoid providing too many actions at once and overwhelming the business.

[0090] If it is determined that the target plugin is not installed in the target store's backend, the merchant will be guided to install the target plugin through the aforementioned pending confirmation action card. The plugin's configuration page will then redirect to the value configuration page, where the suggested parameter values ​​will be used as the initial configuration and pre-filled into the target field configuration form after installation. The configuration form will then take effect upon the merchant's confirmation and save operation.

[0091] If it is determined that the plugin has already been installed in the target store's backend, the target plugin, the suggested parameter values ​​for the configuration fields, and the expected impact of configuring according to the suggested parameter values ​​will be displayed through the aforementioned pending action card. The merchant can then modify the parameter values ​​of the configuration fields themselves, or, after the merchant confirms, the configuration page will be automatically redirected to the configuration page via a link to update the parameter values ​​of the configuration fields to the suggested parameter values.

[0092] In one possible implementation, to provide a reference for subsequent store operation optimization, the server records the root cause indicators, optimization suggestions, and executed actions obtained from the current operation analysis of the target store (which configuration fields of the target plugin were updated, and what parameter values ​​were updated, etc.). The changes in relevant indicators after executing these actions are compared in the operation analysis report of the next operating cycle to evaluate the actual effect of the optimization suggestions. This effect is then fed back into the anomaly detection and optimization suggestion generation for the next business indicator, creating a cycle of diagnosis, execution, and review in the operation analysis report. Specifically, the process can be as follows: After the aforementioned actions are performed, the server records an execution record. This record includes the target store's identifier, the root cause indicator identified in this analysis, optimization suggestions, the actions performed, the execution time, and the data for the root cause indicator and the target business indicator in the first operating cycle. When generating the next operational analysis report for this target store, the server queries the most recent execution record for the target store and compares the data for the root cause indicator and the target business indicator in that record with the corresponding business indicator data calculated in this analysis. Based on the comparison results, the server generates an effectiveness evaluation conclusion and writes it into the generated operational analysis report.

[0093] If, based on the comparison results, it is determined that the root cause indicator has improved to a specified level, then the previous optimization suggestion is deemed effective. The specified level can be an improvement exceeding a specified threshold, or an improvement reaching a specified threshold. The specified threshold can be fixed or dynamic. Furthermore, the confidence level of the operational optimization strategy corresponding to the optimization suggestion for the upward adjustment action is determined in the knowledge base.

[0094] If, based on the comparison results, it is determined that the improvement of the root cause indicator has not reached the specified level, then the effect of the previous optimization suggestion is deemed insufficient, and the confidence level of the business optimization strategy to which the corresponding optimization suggestion belongs in the knowledge base is lowered.

[0095] Confidence levels can be adjusted using fixed increments. For example, when an optimization suggestion is deemed effective, the confidence level of the corresponding business optimization strategy is increased by 0.1, with an upper limit of 1.0. When an optimization suggestion is deemed insufficient, the confidence level of the corresponding business optimization strategy is decreased by 0.1, with a lower limit of 0.1. Confidence levels can be recorded and adjusted at the store level, corresponding to each store, to personalize the RAG search results ranking for each store. Confidence levels can also be recorded and adjusted at the industry category level.

[0096] For example, when the conversion rate is abnormal in the Ath (positive integer)th business cycle, two business optimization strategies are retrieved: optimizing the product detail page and recovering abandoned orders. The semantic relevance score for optimizing the product detail page is 0.9, the confidence score is 0.4, and the overall score is 0.6 × 0.9 + 0.4 × 0.4 = 0.70, where 0.6 and the first 0.4 are weighted values. The semantic relevance score for recovering abandoned orders is 0.8, the confidence score is 0.5, and the overall score is 0.6 × 0.8 + 0.4 × 0.5 = 0.68, where 0.6 and 0.4 are weighted values. The product detail page optimization strategy, with its higher overall score, is prioritized for recall. In the A+1th business cycle, if the product detail page optimization strategy is deemed insufficient, the confidence score for optimizing the product detail page is lowered from 0.4 to 0.3. When the conversion rate becomes abnormal again in the A+2th business cycle, a new search is performed. The overall score of the optimized product details page becomes 0.6×0.9+0.4×0.3=0.66, which is lower than the overall score of 0.68 for recovering abandoned orders. Therefore, the recovered abandoned orders are ranked first and prioritized for recall.

[0097] For example, the business analysis report for the B (positive integer)th business cycle determines that sales have abnormally declined, with the root cause being the conversion rate, which dropped from 4.4% to 4.0%. The recommended optimization is to optimize the product detail page, with the corresponding target plugin being the SEO plugin. After the merchant confirms the implementation, the server records the execution record, which shows that the conversion rate for the Bth business cycle was 4.0%. When the business analysis report for the B+1th business cycle is generated, this execution record is retrieved, and the conversion rate for this business cycle is compared to the previous one, showing a recovery from 4.0% to 4.4%, returning to the level before the anomaly occurred. The optimization recommendation is deemed effective, and the report for the B+1th business cycle outputs a review conclusion: "Product detail page optimization was implemented last week, and the conversion rate recovered from 4.0% to 4.4% this week." The confidence level of the product detail page optimization strategy is increased, and the recommendation will not be pushed again. Conversely, if the conversion rate remains at 4.0% or continues to decline in the B+1th operating cycle, the optimization suggestion is deemed insufficient, and the confidence level for optimizing the product details page is lowered when generating the operating report for the B+1st operating cycle.

[0098] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0099] Based on the same technical concept, embodiments of this application also provide a data analysis apparatus, which can be applied to a server, such as... Figure 4 As shown, the device includes an acquisition module 410 and an analysis module 420, wherein: The acquisition module 410 is used to acquire first data corresponding to the target business indicators of the target store in the first operating cycle, second data corresponding to the target business indicators of the target store in the second operating cycle, and third data corresponding to the target business indicators of the target store within a specified time range. The target business indicators include one or more of the following: sales revenue, average order value, number of visitors, number of orders, and conversion rate. Analysis module 420 is used to determine the abnormal change threshold corresponding to the target business indicator based on the third data corresponding to the target business indicator of the target store within a specified time range, wherein the specified time range includes N operating cycles, and N is an integer greater than 2; and to determine whether there is an abnormality in the target business indicator based on the first data, the second data and the abnormal change threshold.

[0100] In one possible implementation, the analysis module 420 is used for: For the data corresponding to the target business indicators in each of the N operating cycles, calculate the month-on-month change rate of the target business indicators in the two adjacent operating cycles. Based on the month-on-month change rate of the target business indicator within the two adjacent operating cycles, a month-on-month change rate threshold corresponding to the target business indicator is determined, which is used as the abnormal change threshold.

[0101] In one possible implementation, the analysis module 420 is used for: If the operating cycle of the target store within the specified time range is N, then based on the third data corresponding to the target business indicator of the target store within the specified time range, the month-on-month change rate threshold corresponding to the target business indicator is determined.

[0102] In one possible implementation, the analysis module 420 is used for: If the operating cycle of the target store within the specified time range is less than N, then based on the fourth data corresponding to the target business indicator of similar stores within the specified time range, a month-on-month change rate threshold corresponding to the target business indicator is determined. Here, the similar stores are those of the same type as the target store and whose store size meets the similarity criteria.

[0103] In one possible implementation, the analysis module 420 is further configured to: Based on whether the target business indicators are abnormal, an operational analysis report for the target store is generated using a pre-trained Large Language Model (LLM). The operational analysis report is used to indicate the operational status of the target store and optimization strategies for the operational status.

[0104] In one possible implementation, the analysis module 420 is used for: Based on whether the target business indicators are abnormal, RAG is generated through enhanced retrieval, and business optimization strategies are retrieved. Based on the first data, the second data, and the business optimization strategy, an business analysis report for the target store is generated using LLM.

[0105] In one possible implementation, the analysis module 420 is used for: If the target business indicator is abnormal, perform root cause analysis on the target business indicator to obtain the root cause indicator of the abnormality, and retrieve the business optimization strategy associated with the root cause indicator through RAG. If the target business metrics are not abnormal, then the RAG is used to retrieve operational optimization strategies associated with increasing sales.

[0106] In one possible implementation, the business analysis report includes at least one optimization suggestion generated based on the business optimization strategy, wherein each optimization suggestion corresponds to source information and confidence level.

[0107] In one possible implementation, the apparatus further includes an execution module for: If the optimization suggestions included in the business analysis indicate that the target plugin should be optimized, the optimization suggestions for the target plugin will be displayed on the terminal. In response to the confirmation of the optimization suggestions for the target plugin, the configuration of the target plugin is updated according to the optimization suggestions.

[0108] In the technical solution provided in this application, an abnormal change threshold corresponding to the target business indicator is dynamically generated based on the data corresponding to the target business indicator of the target store within a specified time range. Then, based on the abnormal change threshold, the first data corresponding to the target business indicator of the target store in the first operating cycle and the second data corresponding to the target business indicator in the second operating cycle are analyzed to determine whether there is an abnormality in the target business indicator. Compared with manual analysis, this method is more efficient.

[0109] It should be noted that the data analysis apparatus provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the server can be divided into different functional modules to complete all or part of the functions described above. In addition, the data analysis apparatus and the data analysis method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0110] Figure 5 This illustration shows a structural block diagram of a terminal 800 provided in an exemplary embodiment of this application. The terminal 800 may be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 800 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0111] Typically, terminal 800 includes a processor 801 and a memory 802.

[0112] Processor 801 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 801 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 801 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 801 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 801 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0113] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 802 are used to store at least one instruction, which is executed by the processor 801 to implement the data analysis method provided in the method embodiments of this application.

[0114] In some embodiments, the terminal 800 may also optionally include a peripheral device interface 803 and at least one peripheral device. The processor 801, memory 802, and peripheral device interface 803 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 803 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 804, a display screen 805, a camera assembly 806, an audio circuit 807, a positioning assembly 808, and a power supply 809.

[0115] Peripheral device interface 803 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 801 and memory 802. In some embodiments, processor 801, memory 802 and peripheral device interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 801, memory 802 and peripheral device interface 803 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0116] The radio frequency (RF) circuit 804 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 804 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 804 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 804 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 804 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0117] Display screen 805 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 805 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 801 for processing. In this case, display screen 805 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 805, disposed on the front panel of terminal 800; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 800 or in a folded design; in other embodiments, display screen 805 may be a flexible display screen, disposed on a curved or folded surface of terminal 800. Furthermore, display screen 805 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 805 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0118] The camera assembly 806 is used to acquire images or videos. Optionally, the camera assembly 806 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 806 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0119] The audio circuit 807 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 801 for processing, or input to the radio frequency circuit 804 to achieve voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located at a different part of the terminal 800. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 807 may also include a headphone jack.

[0120] The positioning component 808 is used to determine the current geographical location of the positioning terminal 800 in order to enable navigation or LBS (Location Based Service). The positioning component 808 can be a positioning component based on GPS (Global Positioning System), BeiDou system, or Galileo system.

[0121] Power supply 809 is used to supply power to the various components in terminal 800. Power supply 809 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 809 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0122] In some embodiments, the terminal 800 further includes one or more sensors 810. The one or more sensors 810 include, but are not limited to: an accelerometer 811, a gyroscope 812, a pressure sensor 813, a fingerprint sensor 814, an optical sensor 815, and a proximity sensor 816.

[0123] Accelerometer 811 can detect the magnitude of acceleration on the three coordinate axes of a coordinate system established by terminal 800. For example, accelerometer 811 can be used to detect the components of gravitational acceleration on the three coordinate axes. Processor 801 can control display screen 805 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 811. Accelerometer 811 can also be used for games or for acquiring user motion data.

[0124] The gyroscope sensor 812 can detect the orientation and rotation angle of the terminal 800. The gyroscope sensor 812, in conjunction with the accelerometer sensor 811, can collect 3D motion data from the user on the terminal 800. Based on the data collected by the gyroscope sensor 812, the processor 801 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0125] The pressure sensor 813 can be disposed on the side bezel of the terminal 800 and / or on the lower layer of the display screen 805. When the pressure sensor 813 is disposed on the side bezel of the terminal 800, it can detect the user's grip signal on the terminal 800, and the processor 801 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 813. When the pressure sensor 813 is disposed on the lower layer of the display screen 805, the processor 801 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 805. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0126] The fingerprint sensor 814 is used to collect the user's fingerprint. The processor 801 identifies the user's identity based on the fingerprint collected by the fingerprint sensor 814, or the fingerprint sensor 814 identifies the user's identity based on the collected fingerprint. When the user's identity is identified as trusted, the processor 801 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, making payments, and changing settings. The fingerprint sensor 814 can be located on the front, back, or side of the terminal 800. When the terminal 800 has a physical button or manufacturer logo, the fingerprint sensor 814 can be integrated with the physical button or manufacturer logo.

[0127] An optical sensor 815 is used to collect ambient light intensity. In one embodiment, the processor 801 can control the display brightness of the display screen 805 based on the ambient light intensity collected by the optical sensor 815. Specifically, when the ambient light intensity is high, the display brightness of the display screen 805 is increased; when the ambient light intensity is low, the display brightness of the display screen 805 is decreased. In another embodiment, the processor 801 can also dynamically adjust the shooting parameters of the camera assembly 806 based on the ambient light intensity collected by the optical sensor 815.

[0128] The proximity sensor 816, also known as a distance sensor, is typically located on the front panel of the terminal 800. The proximity sensor 816 is used to detect the distance between the user and the front of the terminal 800. In one embodiment, when the proximity sensor 816 detects that the distance between the user and the front of the terminal 800 is gradually decreasing, the processor 801 controls the display screen 805 to switch from a screen-on state to a screen-off state; when the proximity sensor 816 detects that the distance between the user and the front of the terminal 800 is gradually increasing, the processor 801 controls the display screen 805 to switch from a screen-off state to a screen-on state.

[0129] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on terminal 800 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0130] This application embodiment also provides a server 1100, which can be the backend server mentioned in the above embodiments. For example... Figure 6 As shown, server 1100 includes: bus 1102, processor 1104, memory 1106, and communication interface 1108. Processor 1104, memory 1106, and communication interface 1108 communicate with each other via bus 1102. It should be understood that this application does not limit the number of processors and memory in server 1100.

[0131] Bus 1102 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus 1104 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 1104 may include a path for transmitting information between various components of the server 1100 (e.g., memory 1106, processor 1104, communication interface 1108).

[0132] The processor 1104 may include any one or more processors such as CPU (central processing unit), GPU (graphics processing unit), or DSP (digital signal processor).

[0133] The memory 1106 may include volatile memory, such as RAM (random access memory). The memory 1106 may also include non-volatile memory, such as ROM (read-only memory), flash memory, HDD (hard disk drive), or SSD (solid state drive).

[0134] The memory 1106 stores executable program code, and the processor 1104 executes the executable program code to implement a data analysis method.

[0135] The communication interface 1108 is used to enable communication between the server 1100 and other devices or communication networks.

[0136] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a processor in a server to perform the data analysis method described above. This computer-readable storage medium may be non-transitory. For example, the computer-readable storage medium may be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage devices, etc.

[0137] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals (including but not limited to signals transmitted between the user server and other devices) involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, all images and faces involved in this application were obtained with full authorization.

[0138] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0139] It should be understood that "multiple" as used herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0140] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A data analysis method, characterized in that, The method includes: The system obtains the first data corresponding to the target business indicators of the target store in the first operating cycle, the second data corresponding to the target business indicators of the target store in the second operating cycle, and the third data corresponding to the target business indicators of the target store within a specified time range. The target business indicators include one or more of the following: sales revenue, average order value, number of visitors, number of orders, and conversion rate. The specified time range includes N operating cycles, where N is an integer greater than 2. Based on the third data corresponding to the target business indicators of the target store within a specified time range, determine the abnormal change threshold corresponding to the target business indicators; Based on the first data, the second data, and the abnormal change threshold, it is determined whether the target business indicator is abnormal.

2. The method according to claim 1, characterized in that, The step of determining the abnormal change threshold corresponding to the target business indicator based on the third data corresponding to the target business indicator of the target store within a specified time range includes: For the data corresponding to the target business indicators in each of the N operating cycles, calculate the month-on-month change rate of the target business indicators in the two adjacent operating cycles. Based on the month-on-month change rate of the target business indicator within the two adjacent operating cycles, a month-on-month change rate threshold corresponding to the target business indicator is determined, which is used as the abnormal change threshold.

3. The method according to claim 1, characterized in that, The step of determining the abnormal change threshold corresponding to the target business indicator based on the third data corresponding to the target business indicator of the target store within a specified time range includes: If the operating cycle of the target store within the specified time range is N, then based on the third data corresponding to the target business indicator of the target store within the specified time range, the abnormal change threshold corresponding to the target business indicator is determined.

4. The method according to claim 3, characterized in that, The method further includes: If the operating cycle of the target store within the specified time range is less than N, then based on the fourth data corresponding to the target business indicator of the similar stores corresponding to the target store within the specified time range, the month-on-month change rate threshold corresponding to the target business indicator is determined, wherein the similar stores are stores of the same type as the target store and whose store size meets the similarity condition.

5. The method according to claim 1, characterized in that, The method further includes; Based on whether the target business indicators are abnormal, a business analysis report for the target store is generated using a pre-trained Large Language Model (LLM). The business analysis report is used to indicate the business status of the target store and optimization strategies for the business status.

6. The method according to claim 5, characterized in that, The step of generating an operational analysis report for the target store based on whether there are any anomalies in the target business indicators, using a pre-trained LLM, includes: Based on whether the target business indicators are abnormal, RAG is generated through enhanced retrieval, and business optimization strategies are retrieved. Based on the first data, the second data, and the business optimization strategy, an business analysis report for the target store is generated using LLM.

7. The method according to claim 6, characterized in that, The step of generating a Reliable Area Code (RAG) based on whether the target business metrics are abnormal, and retrieving operational optimization strategies, includes: If the target business indicator is abnormal, perform root cause analysis on the target business indicator to obtain the root cause indicator of the abnormality, and retrieve the business optimization strategy associated with the root cause indicator through RAG. If the target business metrics are not abnormal, then the RAG is used to retrieve operational optimization strategies associated with increasing sales.

8. The method according to claim 6, characterized in that, The business analysis report includes at least one optimization suggestion generated based on the business optimization strategy, wherein each optimization suggestion corresponds to source information and confidence level.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: If the optimization suggestions included in the business analysis indicate that the target plugin should be optimized, the optimization suggestions for the target plugin will be displayed on the terminal. In response to the confirmation of the optimization suggestions for the target plugin, the configuration fields of the target plugin are updated according to the optimization suggestions.

10. A data analysis apparatus, characterized in that, The device includes: The acquisition module is used to acquire the first data corresponding to the target business indicators of the target store in the first operating cycle, the second data corresponding to the target business indicators of the target store in the second operating cycle, and the third data corresponding to the target business indicators of the target store within a specified time range. The target business indicators include one or more of the following: sales revenue, average order value, number of visitors, number of orders, and conversion rate. The specified time range includes N operating cycles, where N is an integer greater than 2. The analysis module is used to determine the abnormal change threshold corresponding to the target business indicator based on the third data corresponding to the target business indicator within a specified time range of the target store; and to determine whether there is an anomaly in the target business indicator based on the first data, the second data and the abnormal change threshold.

11. The apparatus according to claim 10, characterized in that, The analysis module is used for: For the data corresponding to the target business indicators in each of the N operating cycles, calculate the month-on-month change rate of the target business indicators in the two adjacent operating cycles. Based on the month-on-month change rate of the target business indicator within the two adjacent operating cycles, a month-on-month change rate threshold corresponding to the target business indicator is determined, which is used as the abnormal change threshold.

12. A server, characterized in that, The server includes a processor and a memory, the memory storing at least one instruction that is loaded and executed by the processor to perform the operations performed by the data analysis method as described in any one of claims 1-9.

13. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, which is loaded and executed by a processor to perform the operations performed by the data analysis method as described in any one of claims 1-9.

14. A computer program product, characterized in that, The computer program product stores at least one instruction, which is loaded and executed by a processor to perform the operation of the data analysis method as described in any one of claims 1-9.

Images