Evaluation information processing method and device

Abstract

The invention discloses an evaluation information processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining multiple pieces of evaluation information for a target merchant; for each piece of evaluation information, extracting at least one evaluation theme from the evaluation information; in response to a related topic with a preset problem in the at least one evaluation topic, obtaining an evaluation result of the evaluation information on the preset problem; marking the evaluation information as negative feedback evaluation information for a preset problem in response to the evaluation result meeting a negative feedback condition; and monitoring the target merchant according to the quantity of the negative feedback evaluation information corresponding to the preset problem. According to the embodiment, merchants can be effectively monitored.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for processing evaluation information. Background Technology

[0002] E-commerce platforms bring together numerous merchants. Some merchants may have operational problems, such as false advertising, selling expired goods, exceeding permitted levels of additives, and poor customer service. To ensure the platform's operational order and protect consumer rights, merchant monitoring is necessary. However, due to the differences in the goods sold, business models, and marketing methods among merchants, there is currently a lack of effective monitoring solutions. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for processing evaluation information, which can effectively monitor merchants.

[0004] In a first aspect, embodiments of the present invention provide a method for processing evaluation information, including:

[0005] Obtain multiple review information for the target merchant;

[0006] For each evaluation information, at least one evaluation topic is extracted from the evaluation information; in response to the existence of a related topic of a preset problem in at least one evaluation topic, the evaluation results of the evaluation information on the preset problem are obtained; in response to the evaluation results meeting the negative feedback conditions, the evaluation information is marked as negative feedback evaluation information for the preset problem.

[0007] Based on the number of negative feedback comments corresponding to preset questions, target merchants are monitored and processed.

[0008] Optionally, based on the number of negative feedback comments corresponding to preset questions, the target merchant is monitored and processed, including:

[0009] The proportion of negative feedback is determined based on the number of negative feedback evaluation messages corresponding to the preset questions;

[0010] In response to the quantity of negative feedback evaluation information being between a first quantity threshold and a second quantity threshold, or the proportion of negative feedback being between a first proportion threshold and a second proportion threshold, preset issues are marked as common issues of the target merchants, and negative feedback prompt information is generated for the target merchants.

[0011] If the number of negative feedback comments exceeds the second quantity threshold, or the proportion of negative feedback exceeds the second proportion threshold, the target merchant will be marked as an isolated merchant so that it will not be displayed on the search results page.

[0012] Optionally, after extracting at least one evaluation topic from the evaluation information, the method further includes:

[0013] The evaluation topics and pre-set questions are encoded into text vectors respectively;

[0014] Calculate the similarity value between the text vector of the evaluation topic and the text vector of the preset question;

[0015] In response to a similarity value greater than a similarity threshold, the evaluation topic is determined to be a relevant topic to the preset question.

[0016] Optionally, after obtaining multiple reviews of the target merchant, the process may also include:

[0017] Determine the rating score for each evaluation item for the target merchant;

[0018] Based on the evaluation scores corresponding to each evaluation item, determine the first rating for the target merchant;

[0019] Obtain multiple sampling inspection information for the target merchant, and determine the evaluation score for each sampling inspection information for the target merchant;

[0020] Based on the evaluation scores corresponding to each sampling information, the second rating corresponding to the target merchant is determined;

[0021] Obtain multiple surveillance videos targeting the target merchant, and determine the rating score for each surveillance video for the target merchant;

[0022] The third rating for the target merchant is determined based on the evaluation scores corresponding to each regulatory video.

[0023] The merchant rating corresponding to the target merchant is determined based on the first, second, and third ratings.

[0024] Optionally, a rating score for each regulatory video targeting the merchant can be determined separately, including:

[0025] Behavioral recognition processing of surveillance videos;

[0026] The behavior recognition processing results of the surveillance video indicate that the target merchant has abnormal behavior. Based on the behavior recognition results, the abnormal behavior of the target merchant is determined.

[0027] Based on the abnormal behavior of the target merchant, determine the evaluation score of the target merchant in the monitoring video.

[0028] Optionally, it also includes:

[0029] Receive the user's search command and determine the search keywords in the search command;

[0030] Determine the match value between each candidate merchant and the search keywords;

[0031] The ranking value of each candidate merchant is determined based on the matching value and merchant rating of each candidate merchant.

[0032] Based on the ranking value of each candidate merchant, the candidate merchants are displayed on the search results page corresponding to the search query.

[0033] Optionally, multiple review information for the target merchant can be obtained, including:

[0034] In response to the detection that the delivery personnel have completed the delivery task of the target merchant and that the delivery personnel meet the evaluation criteria for the target merchant, the merchant display data of the target merchant is sent to the delivery personnel's terminal so that the delivery personnel's terminal can display the evaluation interface based on the merchant display data;

[0035] Receive input information returned by the terminal; where the input information is collected by the terminal using the evaluation interface;

[0036] Based on the input information, generate review information for the target merchant.

[0037] Optionally, multiple review information for the target merchant can be obtained, including:

[0038] In response to receiving a merchant evaluation request for the target merchant from the delivery personnel's terminal, determine whether the delivery personnel provided delivery services to the target merchant within the statistical period.

[0039] In response to the fact that the delivery personnel have provided delivery services to the target merchant during the statistical period, the merchant display data of the target merchant is sent to the terminal so that the terminal can display the evaluation interface based on the merchant display data;

[0040] Receive input information returned by the terminal; where the input information is collected by the terminal using the evaluation interface;

[0041] Based on the input information, generate review information for the target merchant.

[0042] Secondly, embodiments of the present invention provide an apparatus for processing evaluation information, comprising:

[0043] The information acquisition module is used to acquire multiple review information for the target merchant;

[0044] The evaluation labeling module is used to extract at least one evaluation topic from each evaluation information; in response to the existence of a related topic of a preset problem in at least one evaluation topic, obtain the evaluation result of the evaluation information on the preset problem; in response to the evaluation result meeting the negative feedback condition, label the evaluation information as negative feedback evaluation information for the preset problem.

[0045] The monitoring and processing module is used to monitor and process target merchants based on the number of negative feedback evaluation messages corresponding to preset issues.

[0046] Thirdly, embodiments of the present invention provide an electronic device, including:

[0047] One or more processors;

[0048] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0049] Fourthly, embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0050] Fifthly, embodiments of the present invention provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method of any of the above embodiments.

[0051] One embodiment of the above invention has the following advantages or beneficial effects: Multiple evaluation information items targeting a target merchant are obtained. If the evaluation topic of the evaluation information contains a related topic of a preset question, then the evaluation information contains content related to the preset question. The evaluation results of the evaluation information on the preset question are obtained. If the evaluation results of the evaluation information meet the negative feedback conditions, the evaluation information is marked as negative feedback evaluation information for the preset question. Finally, the target merchant is monitored and processed according to the number of negative feedback evaluation information corresponding to the preset question. For example, if the number of negative feedback evaluation information is small, it can be ignored. If the number of negative feedback evaluation information is large, the target merchant has a serious problem, and the target merchant is marked as an isolated merchant so that it is not displayed on the search results page.

[0052] The reviews provide a relatively objective and accurate depiction of users' genuine feedback on the merchant. The pre-set questions are configured based on the merchant's monitoring needs. By utilizing multiple reviews and pre-set questions, the merchant can be effectively monitored.

[0053] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0054] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0055] Figure 1 This is a schematic diagram of the process of an evaluation information processing method provided in an embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram of the process of an evaluation information processing method provided in another embodiment of the present invention;

[0057] Figure 3 This is a schematic diagram of the process of a method for determining merchant ratings according to an embodiment of the present invention;

[0058] Figure 4 This is a schematic diagram of the architecture of a merchant rating system provided in one embodiment of the present invention;

[0059] Figure 5 This is a schematic diagram of the process of a method for generating evaluation information according to an embodiment of the present invention;

[0060] Figure 6 This is a schematic diagram illustrating the display effect of an evaluation interface provided in one embodiment of the present invention;

[0061] Figure 7 This is a schematic diagram illustrating the display effect of a list of merchants to be evaluated according to an embodiment of the present invention;

[0062] Figure 8 This is a schematic diagram illustrating the display effect of an evaluation interface provided in another embodiment of the present invention;

[0063] Figure 9 This is a schematic diagram of the structure of an evaluation information processing device provided in one embodiment of the present invention;

[0064] Figure 10 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0065] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0066] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of this invention comply with the relevant provisions of national laws and regulations.

[0067] Figure 1 This is a schematic diagram of a process for processing evaluation information according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0068] Step 101: Obtain multiple review information for the target merchant.

[0069] Feedback information can come from users or delivery personnel. Delivery personnel can rate the merchant after delivery. A limited number of pop-up windows will randomly appear on the delivery personnel's device. These pop-ups are used to rate the merchant's hygiene, etc.

[0070] Step 102: For each evaluation information, extract at least one evaluation topic from the evaluation information.

[0071] Reviews can be in text format. Review topics are keywords or themes extracted from the review information. These topics could include: slow delivery, poor service, stale ingredients, or reasonable prices.

[0072] Topic models can be used to extract at least one evaluation topic from the evaluation information. The topic model can be an LDA (Latent Dirichlet Allocation) model. Evaluation topics can also be keywords extracted from the evaluation information, such as those obtained using the TF-IDF (term frequency–inverse document frequency) method.

[0073] In one embodiment of the present invention, after extracting at least one evaluation topic from the evaluation information, the method further includes: encoding the evaluation topic and the preset question into text vectors respectively; calculating the similarity value between the text vector of the evaluation topic and the text vector of the preset question; and determining that the evaluation topic is a related topic of the preset question in response to the similarity value being greater than a similarity threshold.

[0074] The similarity value between the text vector of the evaluation topic and the text vector of the preset question can be the distance between them. This distance can be the Manhattan distance, Euclidean distance, Chebyshev distance, etc. If the similarity value is greater than a similarity threshold, the evaluation topic is determined to be a relevant topic to the preset question. If the similarity value is not greater than the similarity threshold, the evaluation topic is determined to be an irrelevant topic to the preset question. Evaluation information for irrelevant topics can be disregarded.

[0075] Step 103: In response to a relevant topic in at least one evaluation topic that contains a preset question, obtain the evaluation information for the evaluation result of the preset question.

[0076] Based on specific needs, at least one preset question should be set. Preset questions may include: false advertising, selling expired goods, excessive additives, and poor service attitude. If a topic related to the preset question exists within the evaluation theme corresponding to the evaluation information, then the evaluation information contains relevant content about the preset question, and the evaluation result for the preset question is obtained. The evaluation result may include: sentiment tendency, evaluation score, etc. Sentiment tendency includes: positive, negative, and neutral. Evaluation scores can be on a five-point scale, a ten-point scale, or a percentage scale, etc.

[0077] The evaluation model can be input along with a pre-defined question to obtain the evaluation result of the evaluation information on the pre-defined question. Alternatively, only the evaluation information can be input into the evaluation model to obtain the evaluation result of the evaluation information on the pre-defined question. For example, if the evaluation information is input into an evaluation model based on sentiment analysis, and the output of the evaluation model is negative, then the evaluation result of the evaluation information on the pre-defined question is determined to be negative.

[0078] Step 104: In response to the evaluation result meeting the negative feedback condition, the evaluation information is marked as negative feedback evaluation information for the preset problem.

[0079] Negative feedback conditions can be set according to specific needs. If the evaluation result includes sentiment tendency, the negative feedback condition can be a negative sentiment tendency. If the evaluation result includes an evaluation score, and the evaluation score is out of ten, the negative feedback condition can be an evaluation score less than 5.

[0080] Step 105: Monitor and process the target merchants based on the number of negative feedback comments corresponding to the preset questions.

[0081] Based on the number of negative feedback comments corresponding to preset issues, target merchants are monitored and processed. For example, if the number of negative feedback comments is small, they can be ignored. If the number of negative feedback comments is large, the target merchant has a serious problem and is marked as an isolated merchant so that it is not displayed on the search results page.

[0082] The reviews provide a relatively objective and accurate depiction of users' genuine feedback on the merchant. The pre-set questions are configured based on the merchant's monitoring needs. By utilizing multiple reviews and pre-set questions, the merchant can be effectively monitored.

[0083] Figure 2 This is a schematic diagram of a process for processing evaluation information according to another embodiment of the present invention. Figure 2 As shown, the method includes:

[0084] Step 201: Obtain multiple review information for the target merchant.

[0085] Step 202: For each evaluation information, extract at least one evaluation topic from the evaluation information.

[0086] Step 203: In response to a relevant topic in at least one evaluation topic where a preset question exists, obtain the evaluation information for the evaluation result of the preset question.

[0087] Step 204: In response to the evaluation result meeting the negative feedback condition, the evaluation information is marked as negative feedback evaluation information for the preset problem.

[0088] Step 205: Determine the proportion of negative feedback based on the number of negative feedback evaluation messages corresponding to the preset questions.

[0089] The negative feedback ratio is the ratio of the number of negative feedback evaluation information to the number of evaluation information in step 201.

[0090] Step 206: In response to the quantity of negative feedback evaluation information being between the first quantity threshold and the second quantity threshold, or the proportion of negative feedback being between the first proportion threshold and the second proportion threshold, the preset problem is marked as a common problem of the target merchant, and negative feedback prompt information is generated for the target merchant.

[0091] Based on the monitoring factors, determine the first quantity threshold, the second quantity threshold, the first percentage threshold, and the second percentage threshold. The monitoring factors include at least one of the following: merchant type, preset issues, and the type of preset issues.

[0092] If the number of negative feedback evaluations falls between the first and second quantity thresholds, or the proportion of negative feedback falls between the first and second proportion thresholds, then a certain percentage of the target merchant exhibits a pre-defined problem. This pre-defined problem is then marked as a common problem for the target merchant, and a negative feedback notification is generated specifically for the target merchant. This negative feedback notification serves as a reminder to relevant personnel to monitor the target merchant's operations regarding the pre-defined problem.

[0093] Step 207: In response to the number of negative feedback evaluations exceeding the second quantity threshold, or the proportion of negative feedback exceeding the second proportion threshold, mark the target merchant as an isolated merchant so that the target merchant is not displayed on the search results page.

[0094] If the number of negative feedback reviews exceeds the second threshold, or the proportion of negative feedback exceeds the second threshold, then the target merchant has a serious problem. The target merchant will be marked as an isolated merchant so that it will not be displayed on the search results page, thereby preventing users from purchasing the target merchant's items or services.

[0095] In the embodiments of this invention, different monitoring strategies are determined based on the number of negative feedback evaluation messages corresponding to preset questions. Utilizing different monitoring strategies allows for reasonable monitoring of businesses, achieving better monitoring results and further protecting consumer rights.

[0096] Figure 3 This is a schematic diagram illustrating the flow of a method for determining merchant ratings according to an embodiment of the present invention. Figure 3 As shown, the method includes:

[0097] Step 301: Obtain multiple evaluation information for the target merchant, and determine the evaluation score for each evaluation information for the target merchant.

[0098] The evaluation score for the target merchant can be out of 5, 10, or 100. The evaluation information and the target merchant's information are input into the first scoring model to obtain the evaluation score for the target merchant.

[0099] Step 302: Determine the first rating for the target merchant based on the rating scores corresponding to each evaluation information.

[0100] The mean, maximum, minimum, and weighted sum of the evaluation scores corresponding to each evaluation information can be used to determine the first rating for the target merchant.

[0101] Step 303: Obtain multiple sampling inspection information for the target merchant, and determine the evaluation score for each sampling inspection information for the target merchant.

[0102] A business monitoring system can be established to record businesses' random inspection information. This information can come from data entered by regulatory personnel and imported data from the health inspection and quarantine system. The inspection information allows for the traceability of businesses' raw materials. Businesses with high-quality food sources and high food hygiene standards during random inspections will receive higher evaluation scores.

[0103] The evaluation scores for target merchants in the random inspection can be based on a five-point, ten-point, or one-hundred-point scale. The inspection information includes multiple inspection items and the corresponding inspection data for each item. The inspection items and their corresponding data can be extracted from data entered by regulatory personnel or imported data from the health inspection and quarantine system using technologies such as natural language processing and named entity recognition. The inspection results for each item are then determined using classification and anomaly detection algorithms. Classification algorithms include logistic regression and support vector machines. Anomaly detection algorithms include isolated forests and local anomaly factors.

[0104] Based on the sampling data of the inspected items, the sampling results are determined. The sum of the scores corresponding to each sampling result is used to obtain the evaluation score of the sampling information for the target merchant. For example, if the sampling result is qualified, the corresponding score is 5. If the sampling result is slightly exceeding the standard, the corresponding score is 2. If the sampling result is that the indicator is seriously deviating from the normal range, the corresponding score is 0, and so on.

[0105] Step 304: Determine the second rating for the target merchant based on the evaluation scores corresponding to each sampling information.

[0106] The mean, maximum, minimum, and weighted sum of the evaluation scores corresponding to each sampling information can be used to determine the second rating for the target merchant.

[0107] Step 305: Obtain multiple surveillance videos for the target merchant and determine the evaluation score for each surveillance video for the target merchant.

[0108] Videos filmed of a business's premises, kitchen, etc., can be used as surveillance videos. These videos can be rated on a five-point, ten-point, or one-hundred-point scale.

[0109] In one embodiment of the present invention, determining the evaluation score of each regulatory video for the target merchant includes: performing behavior recognition processing on the regulatory video; responding to the behavior recognition processing result of the regulatory video indicating that the target merchant has abnormal behavior, determining the abnormal behavior of the target merchant based on the behavior recognition result; and determining the evaluation score of the regulatory video for the target merchant based on the abnormal behavior of the target merchant.

[0110] Abnormal behavior refers to actions that do not comply with operational guidelines, such as not wearing a mask or failing to adhere to hygiene standards. The system has a preset total monitoring score. Based on the behavior identification results, at least one abnormal behavior is identified in the target merchant. The score corresponding to each abnormal behavior is subtracted from the total monitoring score to obtain the monitoring video's evaluation score for the target merchant. For example, not wearing a mask corresponds to a score of 1, and failing to adhere to hygiene standards corresponds to a score of 2, etc.

[0111] Step 306: Determine the third rating for the target merchant based on the evaluation scores corresponding to each regulatory video.

[0112] The mean, maximum, minimum, and weighted sum of the evaluation scores corresponding to each regulatory video can be used to determine the third rating for the target merchant.

[0113] Step 307: Determine the merchant rating corresponding to the target merchant based on the first rating, second rating, and third rating.

[0114] The average, maximum, minimum, and weighted sum of the first, second, and third ratings corresponding to the target merchant can be used to determine the merchant rating corresponding to the target merchant.

[0115] In this embodiment of the invention, data from multiple data sources, including evaluation information, random inspection information, and regulatory videos, are integrated to construct a comprehensive merchant rating system. This system monitors merchant operations and intelligently assesses merchant behavior and provides risk warnings.

[0116] In one embodiment of the present invention, the method further includes: receiving a user's search instruction and determining the search keywords in the search instruction; determining the matching value between each candidate merchant and the search keywords; determining the ranking value of each candidate merchant based on the matching value and merchant rating; and displaying each candidate merchant on the search results page corresponding to the search instruction based on the ranking value of each candidate merchant.

[0117] The ranking value can be a weighted sum of the matching value and the merchant rating. Higher matching values ​​and merchant ratings result in a higher ranking value, and the merchant appears more prominently on the search results page. This embodiment of the invention can display merchants with higher ratings at the top of the search results page, recommending more high-quality merchants to users.

[0118] Figure 4 This is a schematic diagram of the architecture of a merchant rating system provided in one embodiment of the present invention. Figure 4 As shown in the embodiments of this application, multi-source data is fused and analyzed. By integrating evaluation information, sampling inspection information, and regulatory videos, a comprehensive merchant rating system is constructed.

[0119] The backend stores merchant ratings for each merchant and aggregates and ranks them across multiple dimensions. Merchants that repeatedly fail to meet the minimum rating threshold are marked as isolated merchants or added to a blacklist.

[0120] The front-end displays merchant ratings to users using star ratings or scores. Merchants with higher ratings receive more exposure and traffic. While users browse merchant information, notification messages are sent to enhance their understanding of the merchants. These messages could include phrases like "I've already ordered from a five-star hygiene merchant, please use with confidence," etc. The front-end can also generate annual reports for merchants, providing users with more information when choosing a business.

[0121] Figure 5 This is a schematic diagram illustrating the flow of a method for generating evaluation information according to an embodiment of the present invention. Figure 5 As shown, the method includes:

[0122] Step 501: In response to the detection that the delivery personnel have completed the delivery task of the target merchant, send the merchant display data of the target merchant to the delivery personnel's terminal.

[0123] Delivery personnel are responsible for delivering items to users' delivery addresses. These personnel can be food delivery drivers, couriers, etc. If a delivery person meets the rating criteria for a target merchant, the system can send the target merchant's display data to the delivery person's terminal. Rating criteria can be set according to business needs. These criteria may include: the delivery person has not rated the target merchant on that day; the delivery person has rated the target merchant less than the first time within the statistical period; the delivery person's total number of ratings within the statistical period is less than the second time, etc.

[0124] Merchant display data may include: the target merchant's identifier, name, address, items to be delivered, and delivery completion time. After receiving the merchant display data from the server, the delivery personnel's terminal displays a review interface based on this data. The delivery personnel can then input reviews and rate the target merchant using this interface.

[0125] Figure 6 This is a schematic diagram illustrating the display effect of an evaluation interface provided in one embodiment of the present invention. For example... Figure 6 As shown, the review interface displays data for each merchant, including their name, the items delivered, and the delivery completion time. The interface also includes input boxes for delivery personnel to enter feedback for the chosen merchant.

[0126] Step 502: Receive the input information returned by the terminal; wherein the input information is collected by the terminal using the evaluation interface.

[0127] Step 503: Generate evaluation information for the target merchant based on the input information.

[0128] The input information can be directly identified as reviews for the target merchant. Alternatively, the input information can be cleaned and formatted to obtain reviews for the target merchant.

[0129] In this embodiment of the invention, the target merchant's review information comes from the delivery personnel. After the delivery personnel complete the delivery task for the target merchant, the server sends the merchant's display data to the delivery personnel's terminal. The terminal displays the review interface. The delivery personnel submit review information based on the review interface, enabling the server to promptly obtain the operating status of each merchant, effectively monitor the merchants, and further protect the legitimate rights and interests of consumers.

[0130] In one embodiment of the present invention, obtaining multiple evaluation information for a target merchant includes: in response to receiving a merchant evaluation request for the target merchant sent by the terminal of a delivery person, determining whether the delivery person provided delivery services to the target merchant during a statistical period; in response to the delivery person providing delivery services to the target merchant during the statistical period, sending merchant display data of the target merchant to the terminal so that the terminal displays an evaluation interface based on the merchant display data; receiving input information returned by the terminal; wherein the input information is collected by the terminal using the evaluation interface; and generating evaluation information for the target merchant based on the input information.

[0131] Merchant display data can be proactively sent from the server to the terminal. The terminal can also proactively send merchant review requests to the server, which then sends the merchant display data back to the terminal based on these requests. The terminal displays a review interface, allowing delivery personnel to submit reviews promptly.

[0132] The terminal monitors the conversations of delivery personnel for risk. If the number of conversations between the delivery personnel and merchants exceeds a threshold, or if keywords are involved in the conversations between the delivery personnel and merchants, or in the conversations between the delivery personnel and consumers, the terminal proactively sends a merchant review request to the server. Keywords are set according to business needs, such as slow food preparation or careless packaging by the merchant.

[0133] If a delivery person completes a delivery task for a merchant but does not rate the merchant, that merchant becomes a merchant awaiting rating. Delivery personnel may fail to rate multiple merchants they have delivered to in a timely manner due to busy schedules, resulting in multiple merchants awaiting rating. If the terminal displays rating interfaces for multiple merchants awaiting rating simultaneously, it will cause display confusion. The terminal determines the number of merchants awaiting rating for each delivery person; if the number of merchants awaiting rating exceeds a first threshold, the terminal generates a list of merchants awaiting rating.

[0134] Figure 7 This is a schematic diagram illustrating the display effect of a list of merchants to be evaluated, provided by an embodiment of the present invention. For example... Figure 7 As shown, the list of merchants to be evaluated displays information for multiple merchants. The terminal receives evaluation instructions from delivery personnel regarding the list of merchants to be evaluated, identifies the merchant corresponding to the evaluation instruction, and displays the evaluation interface of the corresponding merchant for the delivery personnel to evaluate.

[0135] In one embodiment of the present invention, the terminal determines the number of merchants to be evaluated corresponding to the delivery personnel; in response to the number of merchants to be evaluated being greater than a second number threshold, the terminal generates an evaluation interface based on the merchant evaluation information of each merchant to be evaluated.

[0136] Figure 8 This is a schematic diagram illustrating the display effect of an evaluation interface provided in another embodiment of the present invention. For example... Figure 8 As shown, the evaluation interface consists of sub-interfaces for each merchant to be evaluated. These sub-interfaces can be displayed sequentially based on factors such as delivery completion time. Delivery personnel input evaluation information and assign scores within the sub-interfaces for each merchant. This allows delivery personnel to evaluate multiple merchants simultaneously on a single interface, reducing their workload and improving their user experience.

[0137] Figure 9 This is a schematic diagram of the structure of an evaluation information processing device provided in one embodiment of the present invention. Figure 9 As shown, the device includes:

[0138] The information acquisition module 901 is used to acquire multiple review information for the target merchant;

[0139] The evaluation annotation module 902 is used to extract at least one evaluation topic from each evaluation information; in response to the existence of a related topic of a preset problem in at least one evaluation topic, obtain the evaluation result of the evaluation information on the preset problem; in response to the evaluation result meeting the negative feedback condition, annotate the evaluation information as negative feedback evaluation information for the preset problem.

[0140] The monitoring and processing module 903 is used to monitor and process target merchants based on the number of negative feedback evaluation messages corresponding to preset issues.

[0141] Optionally, the monitoring and processing module 903 is specifically used for:

[0142] The proportion of negative feedback is determined based on the number of negative feedback evaluation messages corresponding to the preset questions;

[0143] In response to the quantity of negative feedback evaluation information being between a first quantity threshold and a second quantity threshold, or the proportion of negative feedback being between a first proportion threshold and a second proportion threshold, preset issues are marked as common issues of the target merchants, and negative feedback prompt information is generated for the target merchants.

[0144] If the number of negative feedback comments exceeds the second quantity threshold, or the proportion of negative feedback exceeds the second proportion threshold, the target merchant will be marked as an isolated merchant so that it will not be displayed on the search results page.

[0145] Optionally, the evaluation annotation module 902 is also used for:

[0146] The evaluation topics and pre-set questions are encoded into text vectors respectively;

[0147] Calculate the similarity value between the text vector of the evaluation topic and the text vector of the preset question;

[0148] In response to a similarity value greater than a similarity threshold, the evaluation topic is determined to be a relevant topic to the preset question.

[0149] Optionally, it also includes:

[0150] The rating module is used to determine the rating score for each evaluation piece of information for the target merchant.

[0151] Based on the evaluation scores corresponding to each evaluation item, determine the first rating for the target merchant;

[0152] Obtain multiple sampling inspection information for the target merchant, and determine the evaluation score for each sampling inspection information for the target merchant;

[0153] Based on the evaluation scores corresponding to each sampling information, the second rating corresponding to the target merchant is determined;

[0154] Obtain multiple surveillance videos targeting the target merchant, and determine the rating score for each surveillance video for the target merchant;

[0155] The third rating for the target merchant is determined based on the evaluation scores corresponding to each regulatory video.

[0156] The merchant rating corresponding to the target merchant is determined based on the first, second, and third ratings.

[0157] Optionally, the scoring module is specifically used for:

[0158] Behavioral recognition processing of surveillance videos;

[0159] The behavior recognition processing results of the surveillance video indicate that the target merchant has abnormal behavior. Based on the behavior recognition results, the abnormal behavior of the target merchant is determined.

[0160] Based on the abnormal behavior of the target merchant, determine the evaluation score of the target merchant in the monitoring video.

[0161] Optionally, it also includes:

[0162] The search response module is used to receive the user's search instructions and determine the search keywords in the search instructions;

[0163] Determine the match value between each candidate merchant and the search keywords;

[0164] The ranking value of each candidate merchant is determined based on the matching value and merchant rating of each candidate merchant.

[0165] Based on the ranking value of each candidate merchant, the candidate merchants are displayed on the search results page corresponding to the search query.

[0166] Optionally, the information acquisition module 901 is specifically used for:

[0167] In response to the detection that the delivery personnel have completed the delivery task of the target merchant and that the delivery personnel meet the evaluation criteria for the target merchant, the merchant display data of the target merchant is sent to the delivery personnel's terminal so that the delivery personnel's terminal can display the evaluation interface based on the merchant display data;

[0168] Receive input information returned by the terminal; where the input information is collected by the terminal using the evaluation interface;

[0169] Based on the input information, generate review information for the target merchant.

[0170] Optionally, the information acquisition module 901 is specifically used for:

[0171] In response to receiving a merchant evaluation request for the target merchant from the delivery personnel's terminal, determine whether the delivery personnel provided delivery services to the target merchant within the statistical period.

[0172] In response to the fact that the delivery personnel have provided delivery services to the target merchant during the statistical period, the merchant display data of the target merchant is sent to the terminal so that the terminal can display the evaluation interface based on the merchant display data;

[0173] Receive input information returned by the terminal; where the input information is collected by the terminal using the evaluation interface;

[0174] Based on the input information, generate review information for the target merchant.

[0175] This invention provides an electronic device, comprising:

[0176] One or more processors;

[0177] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0178] This invention provides a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0179] The following is for reference. Figure 10 It shows a schematic diagram of the structure of a computer system 1000 suitable for implementing a terminal device of the present invention. Figure 10The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0180] like Figure 10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the system 1000. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0181] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0182] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs the functions defined above in the system of this invention.

[0183] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0184] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0185] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor, and for example, can be described as: an information acquisition module, an evaluation labeling module, and a monitoring and processing module. The names of these modules do not necessarily limit the module itself; for example, the information acquisition module can also be described as "a module for acquiring multiple evaluation information for a target merchant."

[0186] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0187] Obtain multiple review information for the target merchant;

[0188] For each evaluation information, at least one evaluation topic is extracted from the evaluation information; in response to the existence of a related topic of a preset problem in at least one evaluation topic, the evaluation results of the evaluation information on the preset problem are obtained; in response to the evaluation results meeting the negative feedback conditions, the evaluation information is marked as negative feedback evaluation information for the preset problem.

[0189] Based on the number of negative feedback comments corresponding to preset questions, target merchants are monitored and processed.

[0190] According to the technical solution of this embodiment of the invention, multiple evaluation information for a target merchant are obtained. If the evaluation topic corresponding to the evaluation information contains a related topic of a preset problem, then the evaluation information contains content related to the preset problem, and the evaluation result of the evaluation information on the preset problem is obtained. If the evaluation result of the evaluation information meets the negative feedback condition, the evaluation information is marked as negative feedback evaluation information for the preset problem. Finally, the target merchant is monitored and processed according to the number of negative feedback evaluation information corresponding to the preset problem. For example, if the number of negative feedback evaluation information is small, it can be ignored. If the number of negative feedback evaluation information is large, the target merchant has a serious problem, and the target merchant is marked as an isolated merchant so that it is not displayed on the search results page.

[0191] The review information accurately describes users' genuine feedback on the merchant. The preset questions are pre-set based on the merchant's monitoring needs. Utilizing multiple reviews and preset questions allows for effective monitoring of the merchant.

[0192] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A processing method of evaluating information, characterized by, The method comprises: obtaining a plurality of evaluation information for a target merchant; for each of the evaluation information, extracting at least one evaluation topic from the evaluation information; in response to the presence of a related topic of a preset problem in the at least one evaluation topic, obtaining an evaluation result of the evaluation information on the preset problem; in response to the evaluation result meeting a negative feedback condition, marking the evaluation information as negative feedback evaluation information for the preset problem; monitoring the target merchant according to the number of negative feedback evaluation information corresponding to the preset problem. The monitoring the target merchant according to the number of negative feedback evaluation information corresponding to the preset problem comprises:

2. The method of claim 1, wherein, determining a negative feedback proportion according to the number of negative feedback evaluation information corresponding to the preset problem; in response to the number of negative feedback evaluation information being between a first quantity threshold and a second quantity threshold, or the negative feedback proportion being between a first proportion threshold and a second proportion threshold, marking the preset problem as a common problem of the target merchant, and generating negative feedback prompt information for the target merchant; in response to the number of negative feedback evaluation information being greater than the second quantity threshold, or the negative feedback proportion being greater than the second proportion threshold, marking the target merchant as an isolated merchant, so as to not display the target merchant in a search result page. After the at least one evaluation topic is extracted from the evaluation information, the method further comprises:

3. The method of claim 1, wherein, respectively encoding the evaluation topic and the preset problem into text vectors; calculating a similarity value between the text vector of the evaluation topic and the text vector of the preset problem; in response to the similarity value being greater than a similarity threshold, determining that the evaluation topic is a related topic of the preset problem. After the plurality of evaluation information for the target merchant is obtained, the method further comprises:

4. The method of claim 1, wherein, respectively determining an evaluation score of each of the evaluation information for the target merchant; determining a first score corresponding to the target merchant according to the evaluation scores corresponding to each of the evaluation information; obtaining a plurality of sampling information for the target merchant, and respectively determining an evaluation score of each of the sampling information for the target merchant; determining a second score corresponding to the target merchant according to the evaluation scores corresponding to each of the sampling information; obtaining a plurality of supervision videos for the target merchant, and respectively determining an evaluation score of each of the supervision videos for the target merchant; determining a third score corresponding to the target merchant according to the evaluation scores corresponding to each of the supervision videos; determining a merchant score corresponding to the target merchant according to the first score, the second score and the third score corresponding to the target merchant. The method of respectively determining an evaluation score of each of the supervision videos for the target merchant comprises:

5. The method of claim 4, wherein, performing behavior recognition processing on the supervision video; in response to the behavior recognition processing result of the supervision video indicating that the target merchant has an abnormal behavior, determining the abnormal behavior of the target merchant according to the behavior recognition result; determining the evaluation score of the supervision video for the target merchant according to the abnormal behavior of the target merchant. The method further comprises:

6. The method of claim 1, wherein, receiving a search instruction of a user, and determining a search keyword in the search instruction; ​ determine a matching value between each candidate merchant and the search keyword; determine a ranking value corresponding to each candidate merchant according to the matching value corresponding to each candidate merchant and the merchant score; display each candidate merchant in a search result page corresponding to the search instruction according to the ranking value corresponding to each candidate merchant.

7. The method of claim 1, wherein, The obtaining of the plurality of evaluation information for the target merchant comprises: In response to monitoring that the article delivery personnel complete the delivery task of the target merchant, sending merchant display data of the target merchant to a terminal of the article delivery personnel, so that the terminal displays an evaluation interface according to the merchant display data; receiving input information returned by the terminal; wherein the input information is collected by the terminal using the evaluation interface; generating evaluation information for the target merchant according to the input information.

8. The method of claim 1, wherein, The obtaining of the plurality of evaluation information for the target merchant comprises: In response to receiving a merchant evaluation request for the target merchant sent by a terminal of article delivery personnel, determining whether the article delivery personnel has provided delivery service for the target merchant within a statistical period; In response to the article delivery personnel providing delivery service for the target merchant within a statistical period, sending merchant display data of the target merchant to the terminal, so that the terminal displays an evaluation interface according to the merchant display data; receiving input information returned by the terminal; wherein the input information is collected by the terminal using the evaluation interface; generating evaluation information for the target merchant according to the input information.

9. An evaluation information processing apparatus characterized by comprising: It comprises: An information acquisition module is used to acquire a plurality of evaluation information for a target merchant; An evaluation labeling module is used to extract at least one evaluation theme from the evaluation information for each evaluation information; in response to the presence of a related theme of a preset problem in the at least one evaluation theme, obtaining an evaluation result of the evaluation information on the preset problem; In response to the evaluation result meeting a negative feedback condition, labeling the evaluation information as negative feedback evaluation information for the preset problem; A monitoring processing module is used to monitor and process the target merchant according to the number of negative feedback evaluation information corresponding to the preset problem.

10. An electronic device, comprising: It comprises: One or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-8.

11. A computer readable medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the method of any one of claims 1-8.

12. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-8.

Images