Quality inspection processing method and device for external visiting task, terminal equipment and medium

Abstract

The embodiment of the invention provides a quality inspection processing method and device for an external visiting task, terminal equipment and a medium, and belongs to the technical field of data processing. The method comprises the following steps: determining user information of a visiting object according to a visiting task; performing external visiting communication on the external visiting object according to the user information to obtain external visiting image information and external visiting voice information corresponding to the external visiting object; performing quality inspection on the external visit image information and the external visit voice information to obtain external visit quality; and generating an external visit report of the external visit task according to the external visit quality. And the data quality in the external visiting process can be ensured through quality inspection of the external visiting information. The accuracy and reliability of the external visiting task can be improved, so that the overall level of the business is improved, and the requirements and feedback of the external visiting object can be better known through the external visiting report, so that the customer satisfaction is improved, and the customer relationship is enhanced. And the problems of information asynchronization, possible leakage of user privacy and no credibility of a quality inspection result in the external visiting task in the related technology are also solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a quality inspection processing method, device, terminal equipment and medium for an outbound visit task. Background Art

[0002] The current outbound visits are mainly carried out by offline visits, and the mobile applications in the industry generally only provide a simple task information list function, which is usually a one-way interaction and does not have comprehensive business management attributes. In the actual outbound visits and business development process, salesmen need to handle a large number of information interaction tasks, including querying vehicle location, obtaining personnel communication information, contacting relevant personnel on site, clocking in, recording, uploading on-site photos, and querying various addresses such as unit addresses and household registration addresses. These operations involve complex process management. Due to the lack of online function support, salesmen often communicate through WeChat groups, DingTalk groups, etc. There are many problems with this method, such as the possibility of leakage of sensitive information of customers, the difficulty of effective management of irregular operations involved in the process, and the difficulty of obtaining the latest information of customers. In addition, this communication method will also derive other management problems. Due to the lack of process data support, quality inspection can often only rely on oral judgments from both parties, and the lack of credible data support will also lead to difficulties in management and quality control. Therefore, a quality inspection processing method for outbound visits is urgently needed to solve the problems of information asynchrony, possible leakage of user privacy, and lack of credibility of quality inspection results in outbound visits in related technologies. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a quality inspection processing method, device, terminal equipment and medium for external visit tasks, aiming to solve the problems of information asynchrony, possible leakage of user privacy and unreliable quality inspection results in external visit tasks in related technologies.

[0004] In a first aspect, an embodiment of the present invention provides a quality inspection processing method for an outbound visit task, comprising:

[0005] Obtaining an outbound visit task, and determining user information corresponding to an outbound visit object according to the outbound visit task;

[0006] Conducting an outbound visit communication with the outbound visit object according to the user information, and obtaining outbound visit image information and outbound visit voice information corresponding to the outbound visit object;

[0007] Performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task;

[0008] Generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

[0009] In a second aspect, an embodiment of the present invention provides a quality inspection processing device for an outbound visit task, comprising:

[0010] A data acquisition module, used to obtain an outbound visit task and determine user information corresponding to an outbound visit object according to the outbound visit task;

[0011] A data collection module, used for conducting an outbound visit communication with the outbound visit object according to the user information, and obtaining outbound visit image information and outbound visit voice information corresponding to the outbound visit object;

[0012] A data quality inspection module, used to perform quality inspection on the external visit image information and the external visit voice information to obtain the external visit quality corresponding to the external visit task;

[0013] A report generation module is used to generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

[0014] In the third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of the quality inspection processing method for any external visit task provided in the specification of the present invention are implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the quality inspection processing method for any external visit task provided in the specification of the present invention.

[0016] The embodiment of the present invention provides a quality inspection processing method, device, terminal equipment and medium for an outbound visit task. The method determines the user information of the outbound visit object according to the outbound visit task; performs outbound visit communication with the outbound visit object according to the user information, obtains the outbound visit image information and outbound visit voice information corresponding to the outbound visit object; performs quality inspection on the outbound visit image information and outbound visit voice information to obtain the outbound visit quality; and generates an outbound visit report for the outbound visit task according to the outbound visit quality. Thus, the quality inspection of the outbound visit image information and the outbound visit voice information can ensure that the acquired data can meet certain standards in terms of integrity, accuracy and consistency, thereby reflecting the true situation of the outbound visit process, and then timely discovering problems in the outbound visit process, which not only improves the accuracy and reliability of the outbound visit task, but also improves the overall level of the business. The outbound visit report generated based on the outbound visit quality can not only present the outbound visit process, the outbound visit quality and its feedback on customer needs in detail, but also help identify room for improvement. This information can help the relevant team deeply understand the needs and feedback of the outbound visit object, thereby continuously optimizing services, improving customer satisfaction, and enhancing the maintenance of customer relationships. In addition, this process effectively solves the common problem of information asynchrony in traditional outbound visit tasks. Through centralized data management and real-time quality inspection, it can ensure that all parties have access to the latest information, thereby reducing misunderstandings and communication barriers. At the same time, through strict data management specifications, the risk of user privacy leakage can also be reduced. Finally, the transparency and traceability of quality inspection results enhance the credibility of the data, so that all parties have a more solid foundation when making decisions, and promote the scientific management and continuous improvement of external visit tasks. It also solves the problems of information asynchrony, possible leakage of user privacy, and unreliable quality inspection results in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of a quality inspection method for an outbound visit task provided by an embodiment of the present invention;

[0019] Figure 2 for Figure 1 A flow chart of sub-step S101 of the quality inspection processing method for the outbound visit task;

[0020] Figure 3 for Figure 1 A flow chart of sub-step S103 of the quality inspection processing method for the outbound visit task;

[0021] Figure 4 A schematic diagram of the module structure of a quality inspection processing device for an outbound visit task provided by an embodiment of the present invention;

[0022] Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0025] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] The embodiment of the present invention provides a quality inspection processing method, apparatus, terminal device and medium for an outbound visit task. The quality inspection processing method for an outbound visit task can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant and a wearable device. The terminal device can be a server or a server cluster.

[0027] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 A flowchart of a quality inspection method for an outbound visit task provided in an embodiment of the present invention.

[0029] like Figure 1 As shown, the quality inspection processing method for the external visit task includes steps S101 to S104.

[0030] Step S101: Obtain an outbound visit task, and determine user information corresponding to an outbound visit object according to the outbound visit task.

[0031] For example, before a salesperson initiates an outbound visit, he or she can use the softphone function in the system to communicate with the customer by phone. After determining the specific itinerary, the salesperson will create an outbound visit task in the system. After the system reviews it, it will dispatch the outbound visit task to the corresponding terminal of the corresponding salesperson, thereby obtaining the outbound visit task.

[0032] In addition, the outbound visit tasks are time-sensitive. For example, the task countdown will be carried out within 48 hours after the initiation, and there will be corresponding reminders on the mobile page. If the time limit is exceeded, the salesperson will be subject to subsequent assessment management.

[0033] Exemplarily, data is parsed from the outbound visit task to obtain the outbound visit object and the user information corresponding to the outbound visit object.

[0034] For example, on the mobile page, the data required for the field visit task is provided and all meet the requirements of information compliance. For example, the user information corresponding to the field visit object includes but is not limited to personal basic information, address information (such as household registration address, company address, current address, etc.), contact information of related persons (such as guarantors, immediate family members, etc.), vehicle information, overdue repayment information, etc.

[0035] In one embodiment, the user information corresponding to the external visit object is determined according to the external visit task, specifically, referring to Figure 2 , step S101 includes: sub-step S1011 to sub-step S1013.

[0036] Sub-step S1011, obtaining sensitive information corresponding to the external visit object according to the external visit task.

[0037] Sub-step S1012, determining the target identifier corresponding to the salesperson, and performing information verification on the target identifier to obtain the reliability corresponding to the salesperson.

[0038] Sub-step S1013, desensitizing the sensitive information according to the reliability, and obtaining the user information corresponding to the external visit object.

[0039] For example, since user information involves the privacy information of the external visit object, after parsing the external visit task, the first thing obtained by this application is the sensitive information corresponding to the external visit object, that is, the information after the external visit object is encrypted.

[0040] Exemplarily, determine the target identification of the salesperson. The target identification can be the salesperson's work number, identification or other unique identifier. Make sure that the target identification can uniquely identify each salesperson. Create a verification process to check the validity and authenticity of the target identification. Common verification mechanisms include cross-checking, comparison with internal records, and the use of external verification services (such as identity authentication services). Submit the salesperson's target identification to the verification system for comprehensive verification. The verification content may include identity confirmation, qualification review, etc. Based on the verification results, evaluate the reliability of the salesperson. This can be achieved through a scoring system or a rating system, such as high, medium, and low reliability levels.

[0041] Exemplarily, different sensitive information desensitization strategies are formulated according to the reliability level of the salesperson. For example, a salesperson with high reliability can access more detailed user information, while a salesperson with low reliability can only access desensitized data. Desensitize sensitive information, such as masking, encryption, or data generalization. The degree of desensitization should match the reliability level of the salesperson to protect user privacy. Ensure that access rights to sensitive information are strictly controlled according to the reliability level of the salesperson. A salesperson with high reliability can directly access or view sensitive data, while a salesperson with low reliability can only access processed desensitized data. Generate user information that meets the requirements from the desensitized data. Ensure that the transmission and use of user information complies with privacy protection regulations to avoid data leakage or abuse. Among them, user information can support salespeople in conducting external visits.

[0042] Specifically, the security of sensitive information is ensured through reliability verification and desensitization. First, the salesperson's identity is determined and information verification is performed to assess its reliability. Then, sensitive information is desensitized according to the reliability level, and finally protected user information is generated. This method can effectively balance data access and privacy protection, thereby ensuring information security while meeting business needs.

[0043] Step S102: Conduct an outbound communication with the outbound object according to the user information, and obtain outbound image information and outbound voice information corresponding to the outbound object.

[0044] For example, the visit address and visit content or visit theme corresponding to the visit object are obtained based on user information, and then the salesperson arrives at the visit address and uploads on-site photos, location check-in photos, etc. to obtain visit image information, and uploads on-site recording information and other visit voice information. In addition, process data can also be filled in, such as whether the person has been seen, the person's willingness to repay, current work situation, actual vehicle situation, etc., and then take a photo to determine the visit image information.

[0045] Step S103: Perform quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task.

[0046] For example, the OCR method is used to extract text from the image information of the outbound visit and match it with the management rules for quality inspection to obtain the first quality inspection result; the outbound voice information is first cleaned, the effective content is determined according to the sound wave characteristics, and then the sound is converted into text and matched with the management rules for quality inspection to obtain the second quality inspection result, so that the first quality inspection result and the second quality inspection result are merged to obtain the outbound visit quality corresponding to the outbound visit task. The outbound visit quality can be a score or a level. This application does not make specific restrictions and can be restricted according to actual needs.

[0047] In one embodiment, the quality inspection of the external visit image information and the external visit voice information is performed to obtain the external visit quality corresponding to the external visit task. Specifically, referring to Figure 3 , step S103 includes: sub-step S1031 to sub-step S1033.

[0048] Sub-step S1031, performing position quality inspection on the external visit image information according to the user information to obtain first quality information corresponding to the external visit task.

[0049] Exemplarily, the location information of the visit object is obtained from the user information, including the target location, specific geographic coordinates or descriptive location information. Then, the location information is extracted from the visit image information, such as the geographic tag data embedded in the image (such as GPS information in EXIF ​​data), or the landmark buildings that may be contained in the image. Next, the location information of the visit provided by the user information is compared with the location information extracted from the visit image information. This can be done by calculating the distance between the two, or checking whether the image is located in a preset geographic area. According to the predetermined geographic location requirements, the image shooting is evaluated to see whether it meets the standards, including checking whether the image is shot at the specified location, the accuracy and range requirements of the geographic location. Finally, the first quality information corresponding to the visit task is determined based on the distance between the visit location information provided by the user information and the location information extracted from the visit image information. The closer the distance, the greater the first quality information, and the farther the distance, the smaller the first quality information.

[0050] In some embodiments, performing location quality inspection on the field visit image information according to the user information to obtain the first quality information corresponding to the field visit task includes: obtaining a location identifier and a first user image corresponding to the field visit task according to the user information; performing target recognition on the field visit image information to obtain a landmark image and a second user image corresponding to the field visit image information; performing semantic feature extraction on the landmark image to obtain a semantic feature vector corresponding to the landmark image; performing edge feature extraction on the landmark image to obtain an edge feature vector corresponding to the landmark image; fusing the semantic feature vector and the edge feature vector to obtain a first target feature vector corresponding to the landmark image; obtaining a second target feature vector corresponding to the location identifier, and calculating a first similarity value between the first target feature vector and the second target feature vector; calculating a second similarity value between the first user image and the second user image; and determining the first quality information corresponding to the field visit task according to the first similarity value and the second similarity value.

[0051] For example, the key data required for the field visit task is first extracted from the user information, including the location identifier and the first user image. The location identifier is used to mark the specific identification image that the salesperson needs to follow when shooting the field visit image. The location identifier helps ensure the accuracy and effectiveness of the image shooting. The first user image refers to the image information of the field visit object, confirming the accuracy of the field visit object.

[0052] Exemplarily, when processing the outbound visit image information, target recognition is first performed to obtain the landmark image in the outbound visit image information, and the person image of the outbound visit object in the outbound visit image information is extracted through target recognition technology to obtain the second user image.

[0053] Exemplarily, the CLIP (Contrastive Language-Image Pre-training) model is used to extract semantic features of landmark images to obtain semantic feature vectors of landmark images. This vector describes the content of the landmark image and its meaning in the image. At the same time, edge feature extraction is performed on the landmark image to obtain edge feature vectors of the landmark image, which are used to capture edge information and shape features in the image. These two feature vectors describe the details and structure of the image from different perspectives.

[0054] Exemplarily, the semantic feature vector and the edge feature vector extracted from the landmark image are fused to obtain a first target feature vector of the landmark image. This feature vector integrates the content information and edge information of the image and provides a comprehensive feature description of the landmark image.

[0055] Exemplarily, the location marker is processed similarly. First, the CLIP model is used to extract semantic features of the location marker to obtain the semantic feature vector of the location marker. At the same time, the edge feature of the location marker is extracted to obtain the edge feature vector of the location marker. After the two feature vectors are fused, a second target feature vector corresponding to the location marker is formed. The second target feature vector integrates the content and edge information of the location marker and provides a comprehensive feature description for the location marker.

[0056] Exemplarily, a first similarity value between the first target feature vector and the second target feature vector is calculated. The first similarity value is used to evaluate the similarity between the landmark image and the location mark, so as to determine whether the landmark image meets the mark standard required by the task.

[0057] Exemplarily, a second similarity value is calculated between the first user image and the second user image. The second similarity value is used to evaluate the similarity between the two user images and determine whether the outbound visit image information accurately visits the outbound visit object.

[0058] Exemplarily, a weighted sum is performed based on the first similarity value and the second similarity value to determine the first quality information corresponding to the external visit task. The larger the result of the weighted sum of the first similarity value and the second similarity value, the larger the first quality information; the smaller the result of the weighted sum of the first similarity value and the second similarity value, the smaller the first quality information.

[0059] Specifically, by calculating the similarity between the landmark image and the location identifier, it is possible to effectively determine whether the salesperson has accurately arrived at the designated outbound location. By calculating the similarity between the first user image and the second user image, it is possible to evaluate whether the salesperson has successfully visited the correct outbound object. This helps to improve the effectiveness of outbound activities and ensure that the salesperson's time and resources are used reasonably. This evaluation not only includes the accuracy of the location, but also covers the correctness of the outbound object, thereby providing comprehensive quality control for outbound activities.

[0060] Sub-step S1032: performing content quality inspection on the outbound voice information according to the user information to obtain second quality information corresponding to the outbound task.

[0061] For example, the purpose of the outbound visit task is determined based on the user information, and the text content that the salesperson should convey to the outbound visit object is extracted from the outbound visit purpose. The text content may include business descriptions, product information or other relevant descriptions.

[0062] For example, speech recognition technology is used to perform speech recognition on the outbound voice information to obtain the corresponding initial text information. The initial text information is then analyzed to retrieve whether it contains text content. This is to confirm whether the salesperson has correctly conveyed the required information. Through this retrieval, it can be determined whether the actual communication content of the salesperson meets the requirements of the outbound mission.

[0063] Exemplarily, the second quality information corresponding to the outbound mission is obtained based on the text retrieval results. The text retrieval results reflect the accuracy and completeness of the information conveyed by the salesperson in the outbound mission. By comprehensively considering the consistency of the initial text information and the text content, the communication effect of the outbound mission can be comprehensively evaluated, thereby further improving the quality control of the outbound mission.

[0064] In some embodiments, performing content quality inspection on the outbound visit voice information according to the user information to obtain the second quality information corresponding to the outbound visit task includes: obtaining the target quality inspection rule corresponding to the outbound visit task according to the user information; performing speaker recognition on the outbound visit voice information to obtain the first voice information corresponding to the outbound visit object and the second voice information corresponding to the salesperson; performing voice recognition on the first voice information to obtain the first text content, and performing voice recognition on the second text content to obtain the second text content; performing content quality inspection on the first text content and the second text content according to the target quality inspection rule to obtain the second quality information corresponding to the outbound visit task.

[0065] For example, the content and standards that need to be inspected for the outbound mission are analyzed based on the user information, and then detailed target quality inspection rules are formulated based on the mission requirements. These rules may include standards for information accuracy, content completeness, language standardization, etc.

[0066] For example, speaker recognition technology is used to analyze the voice information of the outbound visit and distinguish the voice of the outbound visit object and the salesperson. This step usually relies on voiceprint recognition technology, which can extract unique biometric features from the voice. The recognition result is associated with the outbound visit voice data to obtain the first voice information of the outbound visit object and the second voice information corresponding to the salesperson.

[0067] For example, the first voice information of the interviewee is converted into the first text content using the voice recognition technology. Similarly, the second voice information of the salesperson is converted into text using the voice recognition technology to obtain the second text content.

[0068] Exemplarily, the obtained first text content and second text content are evaluated according to the target quality inspection rules. This includes comparing whether the text content meets expectations, whether it accurately conveys the requirements of the external visit task, etc. Compare the first text content with the second text content to analyze whether there are deviations or inconsistencies. Check whether the text content meets the set quality inspection standards, such as accuracy, completeness and standardization. Therefore, based on the results of the content quality inspection, the second quality information corresponding to the external visit task is generated. The second quality information reflects the quality and accuracy of information transmission during the external visit, and provides a basis for subsequent task evaluation and improvement.

[0069] Specifically, by formulating target quality inspection rules, we can ensure that the field visit tasks are carried out according to standards, thereby reducing problems. Speaker recognition technology helps to accurately distinguish the voices of the field visit object and the salesperson to prevent information confusion. Speech recognition technology converts speech into text to improve the accuracy and completeness of the records. According to the target quality inspection rules, the quality of the first text content and the second text content is evaluated, so that deviations in information transmission can be identified, ensuring that the information conveyed by the salesperson is consistent with the task requirements, and improving the overall task execution quality and accuracy.

[0070] In some embodiments, performing content quality inspection on the first text content and the second text content according to the target quality inspection rules to obtain the second quality information corresponding to the external visit task includes: obtaining the first quality inspection rule corresponding to the first text content and the second quality inspection rule corresponding to the second text content from the target quality inspection rules; performing key sentence detection on the second text content using the second quality inspection rule to obtain a first quality inspection result; when the first quality inspection result is that the quality inspection passes, performing keyword detection on the first text content using the first quality inspection rule to obtain a second quality inspection result; when the first quality inspection result is that the quality inspection fails, determining the second quality inspection result according to a preset rule; and determining the second quality information corresponding to the external visit task according to the first quality inspection result and the second quality inspection result.

[0071] Exemplarily, a first quality inspection rule related to the first text content and a second quality inspection rule related to the second text content are extracted from the target quality inspection rule. This step involves identifying and assigning appropriate quality inspection rules to ensure that subsequent quality inspection operations are performed according to correct standards.

[0072] Exemplarily, the second quality inspection rule is used to perform key sentence detection on the second text content. Key sentence detection refers to identifying key sentences or information in the text according to the second quality inspection rule to determine whether the information meets the predetermined standard to obtain the first quality inspection result.

[0073] Exemplarily, if the first quality inspection result indicates that the second text content has passed the quality inspection, the first quality inspection rule is continued to be used to perform keyword detection on the first text content. Keyword detection is to extract and verify keywords from the first text content according to the first quality inspection rule to determine whether it meets the standard and obtain the second quality inspection result. If the first quality inspection result shows that the second text content has not passed the quality inspection, the second quality inspection result is determined according to the preset rule. For example, the preset rule is that when the first quality inspection result is that the quality inspection fails, the second quality inspection result is directly determined as failing the quality inspection.

[0074] Exemplarily, the second quality information of the outbound visit task is obtained by fusing the first quality inspection result and the second quality inspection result. If any one of the first quality inspection result or the second quality inspection result is "quality inspection failed", the second quality information is "quality inspection failed". When both quality inspection results are "quality inspection passed", the second quality information will be further obtained based on the accuracy of the keywords in the first text content and the key sentences in the second text content.

[0075] Specifically, through automated key sentence detection and keyword detection, the efficiency of the quality inspection process can be significantly improved and the workload of manual review can be reduced. The application of standardized quality inspection rules can ensure that the quality control of each field visit task is based on the same standards, improving the consistency and repeatability of the results. Automated detection can reduce information loss or misjudgment caused by human interpretation and improper operation, and improve the accuracy and reliability of quality inspection.

[0076] Sub-step S1033: integrating the first quality information and the second quality information to determine the outbound visit quality corresponding to the outbound visit task.

[0077] Exemplarily, the first quality information and the second quality information are weightedly fused to obtain the outbound visit quality corresponding to the outbound visit task.

[0078] Specifically, by performing location quality inspection and content quality inspection on the outbound visit image information and outbound visit voice information respectively, the quality of the outbound visit task can be comprehensively evaluated from multiple dimensions to ensure the comprehensiveness and accuracy of the quality inspection results. By integrating multiple quality inspection information, the errors that may exist in a single data source are avoided, and the reliability of the final quality assessment is improved.

[0079] Step S104: Generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

[0080] For example, by obtaining the analysis process of the quality of the field visits and the corresponding field visit process, an field visit report corresponding to the field visit task is generated. The generation of the field visit report also supports batch generation, and the field visit report can be in the form of a picture or word version; the field visit report can be viewed in real time on the terminal interface, making it convenient to obtain the latest information management and guide the development of business at any time.

[0081] In some embodiments, after generating an outbound visit report corresponding to the outbound visit task based on the outbound visit quality, the method further includes: performing attendance statistics on the outbound visit task to obtain a first statistical result; performing timeliness statistics on the outbound visit task to obtain a second statistical result; performing outbound visit address statistics on the outbound visit task to obtain a third statistical result; and performing energy efficiency statistics based on the first statistical result, the second statistical result, and the third statistical result to obtain outbound visit efficiency information corresponding to the outbound visit task.

[0082] Exemplarily, the attendance data related to the outbound mission is collected and sorted, including the attendance records and attendance time of the outbound personnel, etc. The key indicators such as the attendance times and attendance duration of each salesperson are counted to form the first statistical result.

[0083] Exemplarily, collect and organize time efficiency data related to the outbound visit tasks, such as task start time, completion time, etc. Calculate the completion time of each outbound visit task and the overall time efficiency of the outbound visit task from allocation to completion, so as to summarize the statistical and analysis results to form a second statistical result.

[0084] Exemplarily, the outbound visit address information involved in the outbound visit task is collected and sorted, and the outbound visit frequency of each outbound visit address information is counted, so as to obtain a third statistical result according to the outbound visit frequency.

[0085] Exemplarily, the first statistical result, the second statistical result and the third statistical result are weightedly fused to obtain the outbound visit efficiency information corresponding to the outbound visit task.

[0086] Specifically, the outbound visit efficiency information can help management make more informed decisions based on the outbound visit efficiency information, such as adjusting outbound visit strategies, optimizing staffing, or improving training plans, etc. It can also identify potential problems in a timely manner and provide data support for continuous improvement.

[0087] The embodiment of the present invention provides a quality inspection processing method, device, terminal equipment and medium for an outbound visit task. The method determines the user information of the outbound visit object according to the outbound visit task; performs outbound visit communication with the outbound visit object according to the user information, obtains the outbound visit image information and outbound visit voice information corresponding to the outbound visit object; performs quality inspection on the outbound visit image information and outbound visit voice information to obtain the outbound visit quality; and generates an outbound visit report for the outbound visit task according to the outbound visit quality. Thus, the quality inspection of the outbound visit image information and the outbound visit voice information can ensure that the acquired data can meet certain standards in terms of integrity, accuracy and consistency, thereby reflecting the true situation of the outbound visit process, and then timely discovering problems in the outbound visit process, which not only improves the accuracy and reliability of the outbound visit task, but also improves the overall level of the business. The outbound visit report generated based on the outbound visit quality can not only present the outbound visit process, the outbound visit quality and its feedback on customer needs in detail, but also help identify room for improvement. This information can help the relevant team deeply understand the needs and feedback of the outbound visit object, thereby continuously optimizing services, improving customer satisfaction, and enhancing the maintenance of customer relationships. In addition, this process effectively solves the common problem of information asynchrony in traditional outbound visit tasks. Through centralized data management and real-time quality inspection, it can ensure that all parties have access to the latest information, thereby reducing misunderstandings and communication barriers. At the same time, through strict data management specifications, the risk of user privacy leakage can also be reduced. Finally, the transparency and traceability of quality inspection results enhance the credibility of the data, so that all parties have a more solid foundation when making decisions, and promote the scientific management and continuous improvement of external visit tasks. It also solves the problems of information asynchrony, possible leakage of user privacy, and unreliable quality inspection results in related technologies.

[0088] See also Figure 4 , Figure 4 A quality inspection and processing device 200 for an outbound visit task provided in an embodiment of the present application includes a data acquisition module 201, a data collection module 202, a data quality inspection module 203, and a report generation module 204, wherein the data acquisition module 201 is used to obtain an outbound visit task and determine the user information corresponding to the outbound visit object according to the outbound visit task; the data collection module 202 is used to conduct an outbound visit communication with the outbound visit object according to the user information, and obtain outbound visit image information and outbound visit voice information corresponding to the outbound visit object; the data quality inspection module 203 is used to perform quality inspection on the outbound visit image information and the outbound visit voice information, and obtain the outbound visit quality corresponding to the outbound visit task; the report generation module 204 is used to generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

[0089] In some implementations, during the process of determining the user information corresponding to the outbound visit object according to the outbound visit task, the data acquisition module 201 executes:

[0090] Obtaining sensitive information corresponding to the visit object according to the visit task;

[0091] Determine the target identifier corresponding to the salesperson, and verify the information of the target identifier to obtain the reliability of the salesperson;

[0092] The sensitive information is desensitized according to the reliability to obtain the user information corresponding to the external visit object.

[0093] In some implementations, the data quality inspection module 203 performs, during the process of performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task:

[0094] Performing position quality inspection on the outbound visit image information according to the user information to obtain first quality information corresponding to the outbound visit task;

[0095] Performing content quality inspection on the outbound voice information according to the user information to obtain second quality information corresponding to the outbound task;

[0096] The first quality information and the second quality information are integrated to determine the outbound visit quality corresponding to the outbound visit task.

[0097] In some implementations, the data quality inspection module 203 performs, during the process of performing position quality inspection on the outbound visit image information according to the user information to obtain the first quality information corresponding to the outbound visit task:

[0098] Obtaining a location identifier and a first user image corresponding to the external visit task according to the user information;

[0099] Performing target recognition on the external visit image information to obtain a landmark image and a second user image corresponding to the external visit image information;

[0100] Extracting semantic features from the landmark image to obtain a semantic feature vector corresponding to the landmark image;

[0101] Extracting edge features of the landmark image to obtain an edge feature vector corresponding to the landmark image;

[0102] fusing the semantic feature vector and the edge feature vector to obtain a first target feature vector corresponding to the landmark image;

[0103] Obtaining a second target feature vector corresponding to the position identifier, and calculating a first similarity value between the first target feature vector and the second target feature vector;

[0104] Calculating a second similarity value between the first user image and the second user image;

[0105] The first quality information corresponding to the outbound visit task is determined according to the first similarity value and the second similarity value.

[0106] In some implementations, the data quality inspection module 203 performs, during the process of performing content quality inspection on the outbound voice information according to the user information to obtain the second quality information corresponding to the outbound task:

[0107] Obtaining target quality inspection rules corresponding to the outbound visit task according to the user information;

[0108] Performing speaker recognition on the outbound visit voice information to obtain first voice information corresponding to the outbound visit object and second voice information corresponding to the salesperson;

[0109] Performing voice recognition on the first voice information to obtain first text content, and performing voice recognition on the second text content to obtain second text content;

[0110] The first text content and the second text content are subjected to content quality inspection according to the target quality inspection rule to obtain the second quality information corresponding to the external visit task.

[0111] In some implementations, the data quality inspection module 203 performs, during the process of performing content quality inspection on the first text content and the second text content according to the target quality inspection rule to obtain the second quality information corresponding to the outbound visit task:

[0112] Obtaining a first quality inspection rule corresponding to the first text content and a second quality inspection rule corresponding to the second text content from the target quality inspection rule;

[0113] Using the second quality inspection rule to perform key sentence detection on the second text content to obtain a first quality inspection result;

[0114] When the first quality inspection result is that the quality inspection is passed, the first quality inspection rule is used to perform keyword detection on the first text content to obtain a second quality inspection result;

[0115] When the first quality inspection result is that the quality inspection fails, the second quality inspection result is determined according to a preset rule;

[0116] The second quality information corresponding to the external visit task is determined according to the first quality inspection result and the second quality inspection result.

[0117] In some implementations, after generating the outbound visit report corresponding to the outbound visit task according to the outbound visit quality, the quality inspection processing device 200 of the outbound visit task further performs:

[0118] Performing attendance statistics on the external visit task to obtain a first statistical result;

[0119] Performing time statistics on the external visit tasks to obtain a second statistical result;

[0120] Performing statistics on the outbound address of the outbound visit task to obtain a third statistical result;

[0121] Energy efficiency statistics are performed based on the first statistical result, the second statistical result, and the third statistical result to obtain the outbound visit efficiency information corresponding to the outbound visit task.

[0122] In some implementations, the quality inspection processing device 200 for an outbound visit task may be applied to a terminal device.

[0123] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the quality inspection processing device 200 for the external visit task described above can refer to the corresponding process in the aforementioned quality inspection processing method embodiment for the external visit task, and will not be repeated here.

[0124] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0125] like Figure 5 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0126] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0127] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0128] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] The processor is used to run a computer program stored in a memory, and implement any one of the quality inspection methods for external visit tasks provided by an embodiment of the present invention when executing the computer program.

[0130] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0131] Obtaining an outbound visit task, and determining user information corresponding to an outbound visit object according to the outbound visit task;

[0132] Conducting an outbound visit communication with the outbound visit object according to the user information, and obtaining outbound visit image information and outbound visit voice information corresponding to the outbound visit object;

[0133] Performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task;

[0134] Generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

[0135] In some implementations, during the process of determining the user information corresponding to the outbound visit object according to the outbound visit task, the processor 301 executes:

[0136] Obtaining sensitive information corresponding to the visit object according to the visit task;

[0137] Determine the target identifier corresponding to the salesperson, and verify the information of the target identifier to obtain the reliability of the salesperson;

[0138] The sensitive information is desensitized according to the reliability to obtain the user information corresponding to the external visit object.

[0139] In some implementations, the processor 301 performs, during the process of performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task:

[0140] Performing position quality inspection on the outbound visit image information according to the user information to obtain first quality information corresponding to the outbound visit task;

[0141] Performing content quality inspection on the outbound voice information according to the user information to obtain second quality information corresponding to the outbound task;

[0142] The first quality information and the second quality information are integrated to determine the outbound visit quality corresponding to the outbound visit task.

[0143] In some implementations, the processor 301, in the process of performing position quality inspection on the outbound visit image information according to the user information to obtain the first quality information corresponding to the outbound visit task, executes:

[0144] Obtaining a location identifier and a first user image corresponding to the external visit task according to the user information;

[0145] Performing target recognition on the external visit image information to obtain a landmark image and a second user image corresponding to the external visit image information;

[0146] Extracting semantic features from the landmark image to obtain a semantic feature vector corresponding to the landmark image;

[0147] Extracting edge features of the landmark image to obtain an edge feature vector corresponding to the landmark image;

[0148] fusing the semantic feature vector and the edge feature vector to obtain a first target feature vector corresponding to the landmark image;

[0149] Obtaining a second target feature vector corresponding to the position identifier, and calculating a first similarity value between the first target feature vector and the second target feature vector;

[0150] Calculating a second similarity value between the first user image and the second user image;

[0151] The first quality information corresponding to the outbound visit task is determined according to the first similarity value and the second similarity value.

[0152] In some implementations, the processor 301, in the process of performing content quality inspection on the outbound voice information according to the user information to obtain the second quality information corresponding to the outbound task, executes:

[0153] Obtaining target quality inspection rules corresponding to the outbound visit task according to the user information;

[0154] Performing speaker recognition on the outbound visit voice information to obtain first voice information corresponding to the outbound visit object and second voice information corresponding to the salesperson;

[0155] Performing voice recognition on the first voice information to obtain first text content, and performing voice recognition on the second text content to obtain second text content;

[0156] The first text content and the second text content are subjected to content quality inspection according to the target quality inspection rule to obtain the second quality information corresponding to the external visit task.

[0157] In some implementations, the processor 301, in the process of performing content quality inspection on the first text content and the second text content according to the target quality inspection rule to obtain the second quality information corresponding to the outbound visit task, executes:

[0158] Obtaining a first quality inspection rule corresponding to the first text content and a second quality inspection rule corresponding to the second text content from the target quality inspection rule;

[0159] Using the second quality inspection rule to perform key sentence detection on the second text content to obtain a first quality inspection result;

[0160] When the first quality inspection result is that the quality inspection is passed, the first quality inspection rule is used to perform keyword detection on the first text content to obtain a second quality inspection result;

[0161] When the first quality inspection result is that the quality inspection fails, the second quality inspection result is determined according to a preset rule;

[0162] The second quality information corresponding to the external visit task is determined according to the first quality inspection result and the second quality inspection result.

[0163] In some implementations, after the outbound visit report corresponding to the outbound visit task is generated according to the outbound visit quality, the processor 301 further executes:

[0164] Performing attendance statistics on the external visit task to obtain a first statistical result;

[0165] Performing time statistics on the external visit tasks to obtain a second statistical result;

[0166] Performing statistics on the outbound address of the outbound visit task to obtain a third statistical result;

[0167] Energy efficiency statistics are performed based on the first statistical result, the second statistical result, and the third statistical result to obtain the outbound visit efficiency information corresponding to the outbound visit task.

[0168] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned quality inspection processing method embodiment of the external visit task, and will not be repeated here.

[0169] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the quality inspection processing method for any external visit task provided in the description of the embodiment of the present invention.

[0170] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0171] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0172] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0173] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A quality inspection method for an outbound visit task, characterized in that: The method comprises: Obtaining an outbound visit task, and determining user information corresponding to an outbound visit object according to the outbound visit task; Conducting an outbound visit communication with the outbound visit object according to the user information, and obtaining outbound visit image information and outbound visit voice information corresponding to the outbound visit object; Performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task; Generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

2. The method according to claim 1, characterized in that The determining the user information corresponding to the external visit object according to the external visit task includes: Obtaining sensitive information corresponding to the visit object according to the visit task; Determine the target identifier corresponding to the salesperson, and verify the information of the target identifier to obtain the reliability of the salesperson; The sensitive information is desensitized according to the reliability to obtain the user information corresponding to the external visit object.

3. The method according to claim 1, characterized in that: The performing quality inspection on the outbound visit image information and the outbound visit voice information to obtain the outbound visit quality corresponding to the outbound visit task includes: Performing position quality inspection on the outbound visit image information according to the user information to obtain first quality information corresponding to the outbound visit task; Performing content quality inspection on the outbound voice information according to the user information to obtain second quality information corresponding to the outbound task; The first quality information and the second quality information are integrated to determine the outbound visit quality corresponding to the outbound visit task.

4. The method according to claim 3, characterized in that The performing position quality inspection on the outbound visit image information according to the user information to obtain first quality information corresponding to the outbound visit task includes: Obtaining a location identifier and a first user image corresponding to the external visit task according to the user information; Performing target recognition on the external visit image information to obtain a landmark image and a second user image corresponding to the external visit image information; Extracting semantic features from the landmark image to obtain a semantic feature vector corresponding to the landmark image; Extracting edge features of the landmark image to obtain an edge feature vector corresponding to the landmark image; fusing the semantic feature vector and the edge feature vector to obtain a first target feature vector corresponding to the landmark image; Obtaining a second target feature vector corresponding to the position identifier, and calculating a first similarity value between the first target feature vector and the second target feature vector; Calculating a second similarity value between the first user image and the second user image; The first quality information corresponding to the outbound visit task is determined according to the first similarity value and the second similarity value.

5. The method according to claim 3, characterized in that: The performing content quality inspection on the outbound voice information according to the user information to obtain second quality information corresponding to the outbound task includes: Obtaining target quality inspection rules corresponding to the outbound visit task according to the user information; Performing speaker recognition on the outbound visit voice information to obtain first voice information corresponding to the outbound visit object and second voice information corresponding to the salesperson; Performing voice recognition on the first voice information to obtain first text content, and performing voice recognition on the second text content to obtain second text content; The first text content and the second text content are subjected to content quality inspection according to the target quality inspection rule to obtain the second quality information corresponding to the external visit task.

6. The method according to claim 5, characterized in that The performing content quality inspection on the first text content and the second text content according to the target quality inspection rule to obtain the second quality information corresponding to the external visit task includes: Obtaining a first quality inspection rule corresponding to the first text content and a second quality inspection rule corresponding to the second text content from the target quality inspection rule; Using the second quality inspection rule to perform key sentence detection on the second text content to obtain a first quality inspection result; When the first quality inspection result is that the quality inspection is passed, the first quality inspection rule is used to perform keyword detection on the first text content to obtain a second quality inspection result; When the first quality inspection result is that the quality inspection fails, the second quality inspection result is determined according to a preset rule; The second quality information corresponding to the external visit task is determined according to the first quality inspection result and the second quality inspection result.

7. The method according to any one of claims 1 to 6, characterized in that After generating the outbound visit report corresponding to the outbound visit task according to the outbound visit quality, the method further includes: Performing attendance statistics on the external visit task to obtain a first statistical result; Performing time statistics on the external visit tasks to obtain a second statistical result; Performing statistics on the outbound address of the outbound visit task to obtain a third statistical result; Energy efficiency statistics are performed based on the first statistical result, the second statistical result, and the third statistical result to obtain the outbound visit efficiency information corresponding to the outbound visit task.

8. A quality inspection processing device for an outbound visit task, characterized in that: include: A data acquisition module, used to obtain an outbound visit task and determine user information corresponding to an outbound visit object according to the outbound visit task; A data collection module, used for conducting an outbound visit communication with the outbound visit object according to the user information, and obtaining outbound visit image information and outbound visit voice information corresponding to the outbound visit object; A data quality inspection module, used to perform quality inspection on the external visit image information and the external visit voice information to obtain the external visit quality corresponding to the external visit task; A report generation module is used to generate an outbound visit report corresponding to the outbound visit task according to the outbound visit quality.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the quality inspection processing method for the external visit task as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the quality inspection processing method for the external visit task described in any one of claims 1 to 7.

Images