Work order matching method, device, equipment and storage medium
By acquiring work order datasets and handler attribute information, calculating comprehensive scores, and recommending candidate handlers and work orders, the problem of low work order processing efficiency in existing systems is solved, and efficient matching and allocation of work orders are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA UNITED NETWORK COMM GRP CO LTD
- Filing Date
- 2022-11-28
- Publication Date
- 2026-08-04
AI Technical Summary
In existing work order systems based on bidding or designated dispatch, work order processing efficiency is low, more complex work orders go unprocessed, and administrators spend time and make inaccurate work order assignments, which fails to effectively improve work order processing efficiency.
By acquiring work order datasets and the attribute information of handlers, a comprehensive score is calculated, candidate handlers and work orders are recommended, recommendation information is provided to match target work order handlers, collaborative filtering algorithms and Pearson correlation coefficients are used to predict work order processing capabilities, and work order processing analysis reports are generated and alerts are issued.
This improved the efficiency and accuracy of work order processing, reduced the time administrators spent allocating tasks, ensured that work orders were matched with the appropriate personnel, and improved the overall efficiency of work order processing.
Smart Images
Figure CN115936355B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of data processing technology, and in particular to a work order matching method, apparatus, device and storage medium. Background Technology
[0002] With economic development, information technology advancements characterized by digitalization, informatization, and intelligentization, along with internet business models, have led to digital transformation. In this transformation, consolidation is a crucial and inevitable stage. For city-level telecom operators, consolidation will effectively save resources and further enable dynamic resource allocation, especially in government and enterprise service consolidation scenarios.
[0003] Currently, the most common methods for centralized work order processing among city-level telecom operators are the order-grabbing system and the designated dispatch system. In the order-grabbing system, workers are more willing to process easier work orders, resulting in situations where more difficult work orders go unprocessed. In the designated dispatch system, the work order administrator's understanding of each worker varies, leading to the assignment of unfamiliar work orders to certain workers. In other words, both existing work order models rely on human subjective judgment to match work orders, resulting in low processing efficiency. Summary of the Invention
[0004] This disclosure provides a work order matching method, apparatus, device, and storage medium to improve the efficiency of work order processing.
[0005] To achieve the above objectives, the present disclosure adopts the following technical solution:
[0006] Firstly, a work order matching method is provided, the method including:
[0007] Obtain the work order dataset and attribute information of multiple work order handlers; the work order dataset includes work orders of various types; the attribute information of each work order handler is used to characterize the work order handling status of the work order handler, including work order type, number of work orders of each type that have been handled, and work order types that have not been handled.
[0008] Based on the work order dataset and the attribute information of the work order handlers, recommendation information is determined. The recommendation information is used to indicate the candidate handlers for each work order type and / or the candidate work orders for each work order handler. The candidate handlers for each work order are those whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the work order type. The candidate work orders for each work order handler include those in the work order dataset whose comprehensive score is greater than a second preset score threshold. The comprehensive score is used to characterize the work order handling ability of the work order handler.
[0009] Recommendation information is provided to the first user so that the first user can match the work order to be processed with the target work order handler based on the recommendation information; wherein the work order to be processed is included in the work order dataset.
[0010] In conjunction with the first aspect mentioned above, in one possible implementation, before obtaining the work order dataset, the method further includes:
[0011] A work order to be verified is created based on the work order information input by the second user;
[0012] The work order to be verified is verified based on preset verification rules; wherein, the preset verification rules are used to verify the format of the work order information in the work order to be verified.
[0013] If the work order to be verified passes the verification, the work order is obtained and sent to the work order dataset.
[0014] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0015] For work orders of the same type that the work order handler has already processed, a comprehensive score for the work orders of the same type that the work order handler has already processed is determined based on the attribute information of the work order handler.
[0016] For work orders of types that the work order handler has not processed, the comprehensive score of the work order of types that the work order handler has not processed is determined based on the attribute information of the work order handler's neighboring work order handlers. Among them, the correlation between the work order handler and the work order handler is greater than a preset correlation threshold. The work order types that the neighboring work order handlers have processed include both the work order types that the work order handler has processed and the work order types that have not been processed.
[0017] In conjunction with the first aspect mentioned above, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0018] The comprehensive score for work orders based on the attribute information of the work order handler determines the types of work orders that the work order handler has processed, including:
[0019] Determine the number of work orders of the work order type that the work order handler has processed and the processing satisfaction rate from the work order handler's attribute information.
[0020] A comprehensive score is calculated based on the number of work orders and the satisfaction level with the processing of each work order type.
[0021] In conjunction with the first aspect mentioned above, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0022] The comprehensive score for work orders of types not previously processed by the corresponding work order handler is determined based on the attribute information of nearby work order handlers. This includes:
[0023] The comprehensive score of work orders of types that the current work order handler has not processed is inferred based on the similarity between the current work order handlers and the attribute information of the current work order handlers. The attribute information of the current work order handlers includes the number of work orders corresponding to the types of work orders that the current work order handler has processed and the types of work orders that the current work order handler has not processed, as well as the processing satisfaction.
[0024] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0025] Obtain the list of pending claims from the first user; the list of pending claims includes all work orders in the work order dataset and the candidate work orders corresponding to the target work order handler;
[0026] Send the list of items to be collected to the target work order handler.
[0027] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0028] Create a to-do list that includes information on work orders that have been received and assigned.
[0029] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0030] After processing all pending work orders, the completed work orders, their work order types, and corresponding work order processing data are stored in the historical work order database.
[0031] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0032] Based on the set analysis parameters, retrieve completed work orders, work order types, and work order processing data from the historical work order database;
[0033] A work order processing analysis report is generated based on completed work orders, the types of completed work orders, and the work order processing data.
[0034] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes:
[0035] Get the number of unclaimed pending work orders in the pending work orders;
[0036] An alarm will be issued when the number of unclaimed pending work orders exceeds a preset threshold. Unclaimed pending work orders include those that have not been matched with a target worker.
[0037] Secondly, a work order matching device is provided, the device comprising:
[0038] The work order acquisition module is used to acquire the work order dataset and the attribute information of multiple work order handlers. The work order dataset includes work orders of various types. The attribute information of each work order handler is used to characterize the work order handling status of the handler, including the work order type, the number of work orders of each type that have been handled, and the types of work orders that have not been handled.
[0039] The recommendation information determination module is used to determine recommendation information based on the work order dataset and the attribute information of the work order handlers. The recommendation information is used to indicate the candidate handlers for each work order type and / or the candidate work orders for each work order handler. The candidate handlers for each work order are those whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the work order type. The candidate work orders for each work order handler include those in the work order dataset whose comprehensive score is greater than a second preset score threshold. The comprehensive score is used to characterize the work order handling ability of the work order handler.
[0040] The recommendation module is used to provide recommendation information to the first user, so that the first user can match the target work order handler for the work order to be processed based on the recommendation information; wherein the work orders to be processed are included in the work order dataset.
[0041] In conjunction with the second aspect above, in one possible implementation, the apparatus further includes:
[0042] The work order creation module is used to create work orders to be verified based on the work order information input by the second user.
[0043] The work order verification module is used to verify the work orders to be verified based on preset verification rules; wherein, the preset verification rules are used to verify the format of the work order information in the work order to be verified.
[0044] The work order collection module is used to obtain the work order and send it to the work order dataset when the work order to be verified passes the verification.
[0045] In conjunction with the second aspect above, in one possible implementation, the apparatus further includes:
[0046] The first comprehensive score determination module is used to determine the comprehensive score of work orders of the type of work orders that the work order handler has already processed, based on the attribute information of the work order handler.
[0047] The second comprehensive score determination module is used to determine the comprehensive score of work orders of types that the work order handler has not processed, based on the attribute information of the work order handlers of the adjacent work order handlers corresponding to the work order handler. The correlation between the adjacent work order handlers corresponding to the work order handler and the work order handler is greater than a preset correlation threshold. The types of work orders that the adjacent work order handlers have processed include both the types of work orders that the work order handler has processed and the types of work orders that have not been processed.
[0048] In conjunction with the second aspect above, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0049] The first comprehensive scoring module includes:
[0050] The processed work order data determination unit is used to determine the number of work orders of the work order type that the work order handler has processed and the processing satisfaction rate in the attribute information of the work order handler.
[0051] The comprehensive scoring calculation unit is used to calculate a comprehensive score for the types of work orders that the work order handler has processed, based on the number of work orders and the satisfaction level of the processing.
[0052] In conjunction with the second aspect above, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0053] The second comprehensive scoring module includes:
[0054] The comprehensive score estimation unit is used to estimate the comprehensive score of work orders of types that the current work order handler has not processed, based on the similarity between the current work order handlers and the attribute information of the current work order handlers. The attribute information of the current work order handlers includes the number of work orders corresponding to the types of work orders that the current work order handler has processed and the types of work orders that the current work order handler has not processed, as well as the processing satisfaction.
[0055] In conjunction with the second aspect above, in one possible implementation, the method further includes:
[0056] The pending collection list acquisition module is used to obtain the pending collection list reported by the first user; the pending collection list includes all work orders in the work order dataset and the candidate work orders corresponding to the target work order handler;
[0057] The pending collection list sending module is used to send a pending collection list to the target work order handler.
[0058] In conjunction with the second aspect above, in one possible implementation, the method further includes:
[0059] The to-do list creation module is used to create to-do lists, which include information about work orders that have been received and assigned.
[0060] In conjunction with the second aspect above, in one possible implementation, the method further includes:
[0061] The historical work order database storage module is used to store completed work orders, their work order types, and corresponding work order processing data in the historical work order database after processing the pending work orders.
[0062] In conjunction with the second aspect above, in one possible implementation, the method further includes:
[0063] The work order analysis data acquisition module is used to retrieve completed work orders, work order types, and work order processing data from the historical work order database based on set analysis parameters.
[0064] The analysis report generation module is used to generate work order processing analysis reports based on completed work orders, the type of completed work orders, and the work order processing data.
[0065] In conjunction with the second aspect above, in one possible implementation, the method further includes:
[0066] The Unclaimed Work Order Acquisition Module is used to obtain the number of unclaimed work orders among the pending work orders;
[0067] The alarm module is used to issue an alarm message when the number of unclaimed pending work orders exceeds a preset threshold; among which, unclaimed pending work orders include pending work orders that have not been matched with a target work order handler.
[0068] Thirdly, a work order matching device is provided, the work order matching device comprising: a processor and a memory; wherein the memory is used to store computer execution instructions, and when the work order matching device is running, the processor executes the computer execution instructions stored in the memory to cause the work order matching device to perform the work order matching method as described in the first aspect and any possible implementation thereof.
[0069] Fourthly, this disclosure provides a computer-readable storage medium storing instructions that, when executed by a processor of a work order matching device, enable the work order matching device to perform the work order matching method as described in the first aspect and any possible implementation thereof.
[0070] In this disclosure, the names of the aforementioned work order matching devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of this disclosure, they fall within the scope of the claims of this disclosure and their equivalents.
[0071] These or other aspects of this disclosure will become more readily apparent in the following description.
[0072] The technical solution provided in this disclosure brings at least the following beneficial effects:
[0073] The work order matching method provided in this disclosure includes: acquiring a work order dataset and attribute information of multiple work order handlers; wherein the work order dataset includes work orders of various work order types; the attribute information of each work order handler is used to characterize the work order handling status of the work order handler, including the work order type, the number of work orders of each work order type that have been handled, and the work order types that have not been handled; determining recommendation information based on the work order dataset and the attribute information of the work order handlers; the recommendation information is used to indicate the candidate handlers corresponding to each work order type and / or the candidate work orders corresponding to each work order handler; the candidate handlers corresponding to the work order are work order handlers whose comprehensive score is greater than a first preset score threshold among the work order handlers handling work orders of the work order type, and the candidate work orders corresponding to the work order handlers include work orders in the work order dataset whose comprehensive score is greater than a second preset score threshold; the comprehensive score is used to characterize the work order handling ability of the work order handler; and providing the recommendation information to a first user so that the first user matches a target work order handler for the work order to be processed according to the recommendation information; wherein the work order to be processed is included in the work order dataset. The recommendation information is based on the work order processing capabilities of the personnel handling the work orders. Therefore, providing the recommendation information to the first user allows the first user to accurately match the target work order handler for the work order to be processed, thereby improving the efficiency of work order processing. Work order matching is achieved by identifying candidate handlers corresponding to the work orders to be processed, thus improving the efficiency of work order processing. Attached Figure Description
[0074] Figure 1 This is a flowchart illustrating a work order matching method provided in this disclosure;
[0075] Figure 2 A flowchart illustrating another work order matching method provided in this disclosure;
[0076] Figure 3 This is a schematic diagram of the structure of a work order matching device provided in this disclosure;
[0077] Figure 4This is a schematic diagram of the hardware structure of a work order matching device provided in this disclosure. Detailed Implementation
[0078] The work order matching method, apparatus and storage medium provided in the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.
[0079] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.
[0080] The terms “first” and “second” in this disclosure and its accompanying drawings are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a particular order of objects.
[0081] Furthermore, the terms “comprising” and “having”, and any variations thereof, used in the description of this disclosure are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.
[0082] It should be noted that in this disclosure, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.
[0083] The following is an explanation of the terms used in this application.
[0084] 1. Work order
[0085] A work order is defined as a simple maintenance or manufacturing plan consisting of one or more tasks. It serves as the basis for upper-level departments to issue tasks and for lower-level departments to receive them. A work order can be independent or part of a large project, and it includes the task details.
[0086] 2. Collaborative Filtering Algorithm
[0087] Collaborative filtering is a typical method that leverages collective intelligence. The main idea is to utilize other user groups with similar interests or historical behaviors to predict what the current user might like or what behaviors they might exhibit by analyzing the current user groups' current preferences or behavioral information. It is mainly divided into user-based nearest neighbor recommendation and item-based nearest neighbor recommendation.
[0088] 3. Pearson correlation coefficient
[0089] The Pearson correlation coefficient, used to measure the linear correlation between two variables X and Y, is defined as the quotient of the covariance and standard deviation of the two variables. When using the Pearson correlation coefficient to represent the correlation between two users, the value ranges from -1 to +1, where -1 indicates a strong negative correlation, +1 indicates a strong positive correlation, and 0 indicates no correlation. The formula is:
[0090]
[0091] Where u represents user u, v represents user v, and l u,v This represents the correlation coefficient between user u and user v, where c represents the work order, and r represents the correlation coefficient between user u and user v. u,c This represents the overall score for user u in processing work order c. r represents the average overall score given by user u for processing all work orders. v,c This represents the overall score of user v in processing work order c. This represents the average overall score given by user v for processing all work orders.
[0092] 4. Text-to-Speech (4S) Technology
[0093] 4S is a speech synthesis application that converts files stored on a computer, such as help files or web pages, into natural speech output. 4S not only helps visually impaired people read information on computers but also increases the readability of text documents. 4S applications include voice-driven email and voice-sensitive systems, and are often used in conjunction with voice recognition programs.
[0094] After a work order is created, common allocation methods include order grabbing by individual workers and assignment by administrators. However, during the order grabbing process, employees tend to choose simpler work orders, resulting in a large number of complex work orders remaining unprocessed for extended periods. In such cases, administrators can assign unprocessed work orders, assigning complex ones to designated workers to prevent them from going unattended. However, when assigning work orders, administrators need to make judgments based on their subjective understanding, such as their knowledge of the worker's abilities and their work order processing history, to determine the appropriate worker for each task. This process is time-consuming for administrators and requires strong management skills. Administrators need to have a thorough understanding of each worker's work order processing capabilities and difficulty level, and be proficient in their work order processing experience to ensure accurate allocation of work orders to suitable workers and improve efficiency.
[0095] Furthermore, for employees who process work orders too slowly or in too few work orders, administrators typically use work order assignment and threshold warnings to urge them to improve work order processing efficiency. However, this method cannot effectively help low-productivity employees. For example, employees with low work order processing capabilities actually need to obtain work orders that match their capabilities to increase speed and the number of work orders. However, since administrators may not accurately know the employee's capabilities and assign them responsive work orders, these employees may not actually receive matching work orders, thus failing to effectively improve work order processing efficiency.
[0096] To address the aforementioned technical problem of low efficiency in work order processing, this application provides a work order matching method. Please refer to [link / reference]. Figure 1 The method includes the following steps (S110-S130):
[0097] Step S110: Obtain the work order dataset and attribute information of multiple work order handlers.
[0098] The work order dataset includes work orders of various types; the attribute information of each work order handler is used to characterize the work order handling status of the work order handler, including the work order type, the number of work orders of each type that have been processed, and the types of work orders that have not been processed.
[0099] The work order type is related to the task content within the work order. The work order type can represent the work content and category of the task content. For example, for telecommunications operation service work orders, the work order type can include mobile network type and innovation type. Mobile network type work orders specifically include tasks such as SIM cards and campus cards, while innovation type work orders specifically include tasks such as cloud computing, big data, the Internet of Things, and large-scale security. For work orders generated from the sale of a certain type of home appliance, the work order type can include delivery and installation type and repair type. The specific task content of delivery and installation type work orders involves physical labor such as moving heavy objects, while the specific task content of repair type work orders involves technical labor such as testing and repairing home appliances. Understandably, the work order type should be set according to the specific application scenario. There are no restrictions on the work order type here. For example, if the task content of the work orders is not significantly different, the work order type can also be used to indicate the difficulty level of the task content.
[0100] The attribute information of each work order handler is used to characterize the work order handling status of the handler, such as the types of work orders that have been processed, the number of work orders of each type that have been processed, and the types of work orders that have not been processed.
[0101] Furthermore, when acquiring the work order dataset and the attribute information of multiple work order handlers, the work orders included in the dataset are unclaimed pending work orders that the handlers have not yet processed. These work orders can be created and submitted by sales or customer service personnel based on user needs, or they can be created and submitted by users themselves. The attribute information of the work order handlers can be obtained by analyzing their historical work order processing data.
[0102] Step S120: Determine recommendation information based on the work order dataset and the attribute information of the work order handler.
[0103] Recommendation information is used to indicate the candidate handlers for each type of work order and / or the candidate work orders for each work order handler; the candidate handlers for each work order are those whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the same type; the candidate work orders for each work order handler include those whose comprehensive score is greater than a second preset score threshold in the work order dataset; the comprehensive score is used to characterize the work order handling ability of the work order handler.
[0104] For example, the work order dataset includes work orders of the mobile network type and work orders of the innovation type. The determined recommendation information indicates that the candidate handlers for work orders of the mobile network type are work order handler A and work order handler B, and the candidate handlers for work orders of the innovation type are work order handler A and work order handler C. The recommendation information also indicates that the candidate work orders corresponding to work order handler A are both mobile network type and innovation type work orders, the candidate work orders corresponding to work order handler B are mobile network type work orders, and the candidate work orders corresponding to work order handler C are innovation type work orders.
[0105] When determining recommendation information, the candidate handlers corresponding to a work order are those among all work order handlers whose overall score for that type of work order is greater than a first score threshold. For example, if the first score threshold is 80, and work order handler A has an overall score of 95 for handling mobile network type work orders, work order handler B has an overall score of 85 for handling mobile network type work orders, and work order handler C has an overall score of 75 for handling mobile network type work orders, then the candidate handlers corresponding to mobile network type work orders are work order handlers A and B. The candidate work orders corresponding to a work order handler include work orders in the work order dataset whose overall score is greater than a second preset score threshold. For example, if the second preset score threshold is 80, and work order handler A has an overall score of 95 for handling mobile network type work orders and an 85 score for handling innovation type work orders, then the candidate work orders corresponding to work order handler A are both mobile network type work orders and innovation type work orders. The comprehensive score is used to characterize the work order processing ability of the work order handler. Its calculation method will be introduced later and will not be repeated here.
[0106] Step S130: Provide recommendation information to the first user so that the first user can match the target work order handler for the work order to be processed based on the recommendation information.
[0107] The work orders to be processed are included in the work order dataset.
[0108] After determining the recommended information, it can be provided to a first user, who can be either a work order administrator or a work order handler. For example, if the first user is a work order administrator, after the recommended information is provided to the administrator, the administrator can match target work order handlers for the pending work orders based on the recommended information. For instance, the recommended information might suggest work order handlers A and B for work orders of the mobile network type, and work order handlers A and C for work orders of the innovation type. The administrator can then match work order handler A as the target handler for pending mobile network type work orders in the work order dataset, so that such work orders are assigned to work order handler A. Simultaneously, the administrator can also match work order handler C as the target handler for pending innovation type work orders in the work order dataset, so that such work orders are assigned to work order handler A. Of course, when there are multiple candidate handlers, the administrator can select the target work order handler based on their subjective judgment. If the first user is the work order handler, the work order handler can claim the pending work orders in the work order dataset based on the recommendation information. For example, if the candidate work orders corresponding to work order handler A are mobile network type work orders and innovation type work orders, then work order handler A can choose any candidate work order and match himself as the target work order handler for that candidate work order. If the candidate work order corresponding to work order handler B is a mobile network type work order, then work order handler B can choose a mobile network type work order and match himself as the target work order handler for that candidate work order.
[0109] In conjunction with the above implementation method, before obtaining the work order dataset, the work order dataset can be determined through the following steps (S210-S230). Please refer to [link / reference]. Figure 2 :
[0110] Step S210: Create a work order to be verified based on the work order information input by the second user.
[0111] The second user can be a salesperson or customer service representative. For example, a salesperson can create a work order to be verified based on a customer's order, so that the work order handler can provide service to the customer based on the work order. Alternatively, the second user can be the customer, who can create their own work orders to be verified according to their needs, so that the work order handler can provide service to the customer based on the work order. The second user can be determined based on the specific application.
[0112] When creating a work order to be verified, the corresponding work order type can be selected. For example, when the second user is an employee of a telecommunications operator, the work order type of the work order they create can include multi-level categories. For instance, the first-level category includes mobile network, dual-line, and innovative services. The second-level category is a more detailed classification based on the first-level category. The second-level category for mobile network includes: work mobile phone, campus card; the second-level category for dual-line includes: internet leased line, data leased line, voice leased line, APN leased line, 5GtoB private network, MPLSVPN leased line, group SMS / MMS leased line; the second-level category for innovative services includes: COP, BPO, IDC, ICT, cloud computing, big data, IoT, and large-scale security.
[0113] In addition, the work order can include a detailed description of the business, such as detailed notes on the customer's personalized needs, product quantity requirements, etc.
[0114] Step S220: Verify the work order to be verified based on the preset verification rules; wherein, the preset verification rules are used to verify the format of the work order information in the work order to be verified.
[0115] For example, if the preset verification rules include verifying the number of digits in a mobile phone number, and the work order to be verified includes a mobile phone number, then when verifying the format of the work order information in the work order, the number of digits in the mobile phone number in the work order to be verified can be checked to see if it is within the preset number of digits. If the mobile phone number in the work order to be verified has only 9 digits, while the preset number of digits in the verification rules is 11, then the work order to be verified will fail the verification. The preset verification rules can be determined based on the actual work order content.
[0116] Step S230: If the work order to be verified passes the verification, obtain the work order and send it to the work order dataset.
[0117] Please continue reading. Figure 2 Once a work order passes verification, it can be sent to the work order dataset, also known as the work order pool. The work order dataset can be, but is not limited to, databases such as Graphite, InfluxDB, ES, MySQL, Redis, PgSql, and Oracle.
[0118] Recommendation information, determined based on the work order dataset and the attribute information of work order handlers, is used to indicate the candidate handlers for each work order type and / or the candidate work orders for each work order handler. Specifically, the candidate handlers for each work order type are those whose overall score is greater than a first preset score threshold among the work order handlers processing work orders. The candidate work orders for each handler include those in the work order dataset whose overall score is greater than a second preset score threshold. The overall score characterizes the work order handling ability of the handler.
[0119] In the work order matching method of this application, the comprehensive score can be calculated using the following method:
[0120] First, for work orders of the same type that the work order handler has already processed, the comprehensive score of the work orders of the same type that the work order handler has already processed is determined based on the attribute information of the work order handler.
[0121] Secondly, for work orders of types that the work order handler has not processed, the comprehensive score of the work orders of types that the work order handler has not processed is determined based on the attribute information of the work order handlers of the adjacent work order handlers corresponding to the work order handler. Among them, the correlation between the work order handler and the adjacent work order handlers corresponding to the work order handler is greater than a preset correlation threshold. The work order types that the adjacent work order handlers have processed include the work order types that the work order handlers have processed and the work order types that have not been processed.
[0122] As one implementation method, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction for each type of work order. When determining the comprehensive score of the work order types processed by the work order handler based on the attribute information of the work order handler, the number of work orders processed by the work order handler for each type of work order and the processing satisfaction can be determined first from the attribute information of the work order handler. Then, the comprehensive score of the work order types processed by the work order handler can be calculated based on the number of work orders and the processing satisfaction.
[0123] For example, a comprehensive score is determined from two dimensions: the historical number of work orders processed by the work order handler for a certain type, and the satisfaction level of the customer or administrator with the work order handler for all work orders of that type. The comprehensive score is calculated using a normalized and weighted calculation method, as shown in the following formula:
[0124] Z = P * 30% + Q × 70%
[0125] Where Z represents the overall score, P represents the normalized score of the number of historical work orders of a certain type handled by a work order handler, P = Pt / Pm*10; Pt represents the number of historical work orders of this type handled by the work order handler, Pm represents the number of historical work orders of this type handled by all work order handlers, and Q represents the historical satisfaction score.
[0126] As another implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order. When determining the comprehensive score of work orders of types of work orders not processed by the work order handler based on the attribute information of neighboring work order handlers corresponding to the work order handler, the comprehensive score of work orders of types of work orders not processed by the work order handler can be inferred based on the similarity between neighboring work order handlers and the attribute information of neighboring work order handlers. The attribute information of neighboring work order handlers includes the number of work orders and the processing satisfaction rate corresponding to the work order types processed by the work order handler and the work order types not processed by the work order handler, respectively.
[0127] Specifically, for work order types that a worker hasn't processed, their overall rating can be predicted based on a collaborative filtering algorithm. This involves using the overall ratings of all workers for each work order type, as well as all work orders processed by workers who haven't processed that type and their overall ratings for those work orders. The Pearson correlation coefficient is used to represent the correlation between two workers. This identifies K other workers with similar behaviors or preferences to the current worker's past behavior history; these are called nearest neighbor workers. After calculating the nearest neighbor workers for workers who haven't processed that type of work order, for each type of work order that the worker hasn't processed has never seen, the overall ratings of those workers for that type of work order can be used to infer their overall ratings. For example, if the current work order handler A has not processed any work orders of the moving type, then the Pearson coefficient is used to calculate the work order handler D of work order handler A's nearest work order handler. The comprehensive score of work order handler D's processing of work orders of the moving type can be used as the predicted comprehensive score for work order handler A's processing of work orders of the moving type. Furthermore, there may be multiple nearest work order handlers, and the calculation method for the comprehensive score varies. Understandably, when inferring the comprehensive score based on the attribute information of nearest work order handlers, different methods can be used for prediction. As in the example above, the comprehensive score of the nearest work order handlers can be directly used as the comprehensive score of work order handlers who have not processed this type of work order. Alternatively, algorithms such as neural networks can be used to learn and predict based on the comprehensive scores of nearest work order handlers. The specific inference method is not limited here.
[0128] For example, once the nearest work order handlers are identified, the overall score for that work order handler regarding the unprocessed or unseen work order type can be predicted based on the following formula:
[0129]
[0130] Where score(u, c) represents the overall score given by user u to work order c that it has not processed, u represents the person u who processed the work order c that it has not processed, v represents the person v who processed the work order next to it, and l u,v This represents the correlation coefficient between work order handler u and neighboring work order handlers v, where c represents the work order. r represents the average overall score given by work order handler u for processing all work orders. v,c This represents the overall score of the person (v) who is closest to processing work order c. This represents the average overall score of all work orders processed by the nearest work order handler (v).
[0131] In the process of managing work orders, the status of a work order includes three states: pending collection, processing, and completed. Based on the above implementation methods, the work order matching method also includes the following processes:
[0132] First, obtain the list of pending tasks reported by the first user; the list of pending tasks includes all work orders in the work order dataset and the candidate work orders corresponding to the target work order handler;
[0133] The list of pending collections includes all work orders that are in the pending collection status.
[0134] Then, send the list of items to be collected to the target work order handler.
[0135] In one possible implementation, a to-do list can also be created, which includes information on work orders that have been received and assigned. The to-do list includes all work orders that are in the processing stage.
[0136] The work order matching method further includes: after processing all pending work orders, storing the completed work orders, their work order types, and corresponding work order processing data in the historical work order database. The historical work order database includes work orders in a completed state, where the completed state can include resolved work orders and unresolved voided work orders.
[0137] To ensure that work orders can be analyzed, completed work orders, their types, and processing data can be retrieved from the historical work order database based on the set analysis parameters. A work order processing analysis report can then be generated based on the completed work orders, their types, and processing data.
[0138] For example, in a quantitative analysis requiring the classification of the total number of completed work orders and their types, the set analysis parameters include the number of work orders of each type and the proportion of each type of work order in all work orders. Based on these parameters, relevant data can be obtained, and a work order processing analysis report can be generated. This report may include visually appealing content such as charts and graphs, as well as data for easy comparison. Understandably, work order processing data may also include average response times for all work orders, average response times for different work order types, average satisfaction levels for all work orders, average satisfaction levels for each work order handler, and work order processing time.
[0139] To improve work order processing efficiency, the number of unclaimed work orders can be obtained. When the number of unclaimed work orders exceeds a preset threshold, an alarm is issued. Unclaimed work orders include those not matched with a target handler. Specifically, work order timeouts and congestion can be notified to both the work order handler and the administrator via SMS, while unclaimed work orders can be sent to both the work order handler and the administrator using 4S technology combined with voice broadcasting.
[0140] As can be seen, the above mainly describes the technical solutions provided by the embodiments of this disclosure from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.
[0141] This disclosure embodiment can divide the work order matching device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this disclosure embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.
[0142] like Figure 3 As shown, a work order matching device 300 provided in this embodiment of the present disclosure includes:
[0143] The work order acquisition module 310 is used to acquire a work order dataset and attribute information of multiple work order handlers; the work order dataset includes work orders of various types; the attribute information of each work order handler is used to characterize the work order handling status of the work order handler, including the work order type, the number of work orders of each type that have been handled, and the types of work orders that have not been handled.
[0144] The recommendation information determination module 320 is used to determine recommendation information based on the work order dataset and the attribute information of the work order handlers. The recommendation information is used to indicate the candidate handlers corresponding to each work order type and / or the candidate work orders corresponding to each work order handler. The candidate handlers corresponding to the work orders are the work order handlers whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the work order type. The candidate work orders corresponding to the work order handlers include the work orders in the work order dataset whose comprehensive score is greater than a second preset score threshold. The comprehensive score is used to characterize the work order handling ability of the work order handlers.
[0145] The recommendation module 330 is used to provide recommendation information to the first user so that the first user can match the target work order handler for the work order to be processed based on the recommendation information; wherein the work order to be processed is included in the work order dataset.
[0146] Alternatively, in one possible implementation, the apparatus further includes:
[0147] The work order creation module is used to create work orders to be verified based on the work order information input by the second user.
[0148] The work order verification module is used to verify the work orders to be verified based on preset verification rules; wherein, the preset verification rules are used to verify the format of the work order information in the work order to be verified.
[0149] The work order collection module is used to obtain the work order and send it to the work order dataset when the work order to be verified passes the verification.
[0150] Alternatively, in one possible implementation, the apparatus further includes:
[0151] The first comprehensive score determination module is used to determine the comprehensive score of work orders of the type of work orders that the work order handler has already processed, based on the attribute information of the work order handler.
[0152] The second comprehensive score determination module is used to determine the comprehensive score of work orders of types that the work order handler has not processed, based on the attribute information of the work order handlers of the adjacent work order handlers corresponding to the work order handler. The correlation between the adjacent work order handlers corresponding to the work order handler and the work order handler is greater than a preset correlation threshold. The types of work orders that the adjacent work order handlers have processed include both the types of work orders that the work order handler has processed and the types of work orders that have not been processed.
[0153] Optionally, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0154] The first comprehensive scoring module includes:
[0155] The processed work order data determination unit is used to determine the number of work orders of the work order type that the work order handler has processed and the processing satisfaction rate in the attribute information of the work order handler.
[0156] The comprehensive scoring calculation unit is used to calculate a comprehensive score for the types of work orders that the work order handler has processed, based on the number of work orders and the satisfaction level of the processing.
[0157] Optionally, in one possible implementation, the attribute information includes the number of work orders processed by the work order handler for each type of work order and the processing satisfaction rate for each type of work order.
[0158] The second comprehensive scoring module includes:
[0159] The comprehensive score estimation unit is used to estimate the comprehensive score of work orders of types that the current work order handler has not processed, based on the similarity between the current work order handlers and the attribute information of the current work order handlers. The attribute information of the current work order handlers includes the number of work orders corresponding to the types of work orders that the current work order handler has processed and the types of work orders that the current work order handler has not processed, as well as the processing satisfaction.
[0160] Alternatively, in one possible implementation, the method further includes:
[0161] The pending collection list acquisition module is used to obtain the pending collection list reported by the first user; the pending collection list includes all work orders in the work order dataset and the candidate work orders corresponding to the target work order handler;
[0162] The pending collection list sending module is used to send a pending collection list to the target work order handler.
[0163] Alternatively, in one possible implementation, the method further includes:
[0164] The to-do list creation module is used to create to-do lists, which include information about work orders that have been received and assigned.
[0165] Alternatively, in one possible implementation, the method further includes:
[0166] The historical work order database storage module is used to store completed work orders, their work order types, and corresponding work order processing data in the historical work order database after processing the pending work orders.
[0167] Alternatively, in one possible implementation, the method further includes:
[0168] The work order analysis data acquisition module is used to retrieve completed work orders, work order types, and work order processing data from the historical work order database based on set analysis parameters.
[0169] The analysis report generation module is used to generate work order processing analysis reports based on completed work orders, the type of completed work orders, and the work order processing data.
[0170] Alternatively, in one possible implementation, the method further includes:
[0171] The Unclaimed Work Order Acquisition Module is used to obtain the number of unclaimed work orders among the pending work orders;
[0172] The alarm module is used to issue an alarm message when the number of unclaimed pending work orders exceeds a preset threshold; among which, unclaimed pending work orders include pending work orders that have not been matched with a target work order handler.
[0173] This disclosure provides a work order matching device for executing the method required by any device in the aforementioned data integrity determination system. The work order matching device may be the work order matching device described in this disclosure, or a module within a work order matching apparatus; it may also be a chip within a work order matching device, or other apparatus for executing the work order matching method; this disclosure does not limit its scope.
[0174] When implemented in hardware, the work order matching device in this application embodiment is specifically implemented as follows: Figure 4 As shown, Figure 4 This is a schematic diagram of a work order matching device provided in an embodiment of the present disclosure. The work order matching device 400 includes at least one processor 401, a communication line 402, and at least one communication interface 404, and may also include a memory 403. The processor 401, memory 403, and communication interface 404 are connected to each other via the communication line 402.
[0175] The processor 401 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this disclosure, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).
[0176] Communication line 402 may include a path for transmitting information between the aforementioned components.
[0177] Communication interface 404 is used to communicate with other devices or communication networks. It can use any transceiver-like device, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.
[0178] The memory 403 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of including or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.
[0179] In one possible design, the memory 403 can exist independently of the processor 401, meaning the memory 403 can be an external memory of the processor 401. In this case, the memory 403 can be connected to the processor 401 via a communication line 402 to store execution instructions or application code, and its execution is controlled by the processor 401 to implement the work order matching method provided in the following embodiments of this disclosure. In another possible design, the memory 403 can also be integrated with the processor 401, meaning the memory 403 can be an internal memory of the processor 401. For example, the memory 403 can be a cache, which can be used to temporarily store some data and instruction information.
[0180] As one possible implementation, processor 401 may include one or more CPUs, for example Figure 4 CPU0 and CPU1 in the example. As another possible implementation, the work order matching device 400 may include multiple processors, such as... Figure 4 The processors 401 and 407 are included. Alternatively, the work order matching device 400 may also include an output device 405 and an input device 406.
[0181] Through the above description of the implementation methods, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the network node can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, modules, and network nodes described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0182] This disclosure also provides a computer-readable storage medium storing instructions that, when executed by a computer, perform each step of the method flow shown in the above method embodiments.
[0183] The computer-readable storage medium may 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 computer-readable storage media (a non-exhaustive list) include: 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), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In this embodiment of the disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0184] Embodiments of this disclosure provide a chip including a processor and a communication interface, the communication interface being coupled to the processor. The processor is used to run computer programs or instructions to implement the work order matching method as described in the above method embodiments. Since the apparatus, device, computer-readable storage medium, and computer program product in the embodiments of this disclosure can be applied to the above methods, the technical effects obtained can also be referred to the above method embodiments, and the embodiments of this disclosure will not be repeated here.
[0185] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0186] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0187] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0188] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.
Claims
1. A work order matching method, characterized in that, The method includes: Obtain a work order dataset and attribute information of multiple work order handlers; wherein the work order dataset includes work orders of various types; the attribute information of each work order handler is used to characterize the work order processing status of the work order handler, and the work order processing status includes work order type, number of work orders of each work order type that have been processed, and work order types that have not been processed. Based on the work order dataset and the attribute information of the work order handlers, recommendation information is determined. The recommendation information is used to indicate the candidate handlers corresponding to each work order type and / or the candidate work orders corresponding to each work order handler. The candidate handlers corresponding to the work orders are those whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the work order type. The candidate work orders corresponding to the work order handlers include the work orders in the work order dataset whose comprehensive score is greater than a second preset score threshold. The comprehensive score is used to characterize the work order handling ability of the work order handler. For work orders of the types of work orders that the work order handler has already processed, a comprehensive score for the work orders of the types of work orders that the work order handler has already processed is determined based on the attribute information of the work order handler; the attribute information includes the number of work orders of each type of work order processed by the work order handler and the processing satisfaction of each type of work order. For work orders of types not processed by the specified work order handler, a comprehensive score for the work orders of the types not processed by the specified work order handler is inferred based on the similarity between the specified work order handler and nearby work order handlers, as well as the attribute information of the nearby work order handlers. The attribute information of the nearby work order handlers includes the number of work orders corresponding to the types of work orders already processed by the specified work order handler and the types of work orders not processed by the specified work order handler, respectively, and the processing satisfaction rate. The correlation between the nearby work order handlers corresponding to the specified work order handler and the specified work order handler is greater than a preset correlation threshold. The types of work orders already processed by the nearby work order handlers include both the types of work orders already processed by the specified work order handler and the types of work orders not processed by the specified work order handler. The recommendation information is provided to a first user so that the first user can match a target work order handler for the work order to be processed based on the recommendation information; wherein the work order to be processed is included in the work order dataset.
2. The method according to claim 1, characterized in that, Before obtaining the work order dataset, the method further includes: A work order to be verified is created based on the work order information input by the second user; The work order to be verified is verified based on preset verification rules; wherein, the preset verification rules are used to verify the format of the work order information in the work order to be verified. If the work order to be verified passes the verification, the work order is obtained and sent to the work order dataset.
3. The method according to claim 1, characterized in that, The comprehensive score for work orders based on the attribute information of the work order handler, determining the types of work orders already handled by the work order handler, includes: Determine the number of work orders of the work order type that the work order handler has processed and the processing satisfaction rate from the attribute information of the work order handler; A comprehensive score for the types of work orders processed by the work order handler is calculated based on the number of work orders and the processing satisfaction.
4. The method according to claim 1, characterized in that, The method further includes: Obtain the list of pending claims provided by the first user; the list of pending claims includes all work orders in the work order dataset and the candidate work orders corresponding to the target work order handler; Send the list of items to be claimed to the target work order handler.
5. The method according to claim 1, characterized in that, The method further includes: After processing the pending work orders, the completed work orders, their work order types, and work order processing data are stored in the historical work order database.
6. The method according to claim 5, characterized in that, The method further includes: Based on the set analysis parameters, the completed work orders, the work order types of the completed work orders, and the work order processing data are obtained from the historical work order database. A work order processing analysis report is generated based on the completed work orders, the work order types of the completed work orders, and the work order processing data.
7. The method according to claim 1, characterized in that, The method further includes: Obtain the number of unclaimed work orders among the pending work orders; An alarm is issued when the number of unclaimed pending work orders exceeds a preset threshold; wherein, the unclaimed pending work orders include pending work orders that have not been matched with a target work order handler.
8. A work order matching device, characterized in that, The device includes: The work order acquisition module is used to acquire a work order dataset and attribute information of multiple work order handlers; wherein the work order dataset includes work orders of various types; the attribute information of each work order handler is used to characterize the work order processing status of the work order handler, and the work order processing status includes work order type, number of work orders of each type that have been processed, and work order types that have not been processed. The recommendation information determination module is used to determine recommendation information based on the work order dataset and the attribute information of the work order handlers. The recommendation information is used to indicate the candidate handlers corresponding to each work order type and / or the candidate work orders corresponding to each work order handler. The candidate handlers corresponding to the work orders are those whose comprehensive score is greater than a first preset score threshold among the work order handlers who handle work orders of the work order type. The candidate work orders corresponding to the work order handlers include the work orders in the work order dataset whose comprehensive score is greater than a second preset score threshold. The comprehensive score is used to characterize the work order handling ability of the work order handler. The recommendation information determination module is also used to determine the comprehensive score of the work order types that the work order handler has handled, based on the attribute information of the work order handler; the attribute information includes the number of work orders handled by the work order handler for each type and the processing satisfaction for each type of work order. The recommendation information determination module is further used to, for work orders of types not processed by the work order handler, infer a comprehensive score for the work orders of types not processed by the work order handler based on the similarity between the work order handler and the work order handler and the attribute information of the nearby work order handlers; wherein, the attribute information of the nearby work order handlers includes the number of work orders corresponding to the work order types already processed by the work order handler and the work order types not processed by the work order handler, respectively, and the processing satisfaction; the correlation between the nearby work order handlers corresponding to the work order handler and the work order handler is greater than a preset correlation threshold, and the work order types already processed by the nearby work order handlers include the work order types already processed by the work order handler and the work order types not processed by the work order handler; The recommendation module is used to provide the recommendation information to the first user, so that the first user can match the pending work order with a target work order handler based on the recommendation information; wherein the pending work orders are included in the work order dataset.
9. A work order matching device, characterized in that, include: A processor and a memory; wherein the memory is used to store computer execution instructions, and when the work order matching device is running, the processor executes the computer execution instructions stored in the memory to cause the work order matching device to perform the work order matching method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by the processor of the work order matching device, cause the work order matching device to perform the work order matching method according to any one of claims 1-7.