Intelligent auditing method and device, intelligent recommendation method and device, equipment, medium and program product

Abstract

The invention provides an intelligent auditing method based on a business travel limit, which can be applied to the technical field of big data. The method comprises the steps of obtaining a user level of a user, and determining an initial limit according to the user level; checking to-be-reimbursed data of the user based on the initial quota; in response to the situation that the to-be-reimbursed data is larger than the initial limit, a data set containing consumption data of multiple objects is clustered through a clustering algorithm, multiple consumption data unit prices are obtained, and the consumption data of the multiple objects and the to-be-reimbursed data are consumption data generated by merchants of the same type in a preset address range; and determining a clustering quota according to the multiple consumption data unit prices and a first floating parameter, and auditing the to-be-reimbursed data based on the clustering quota, the first floating parameter being used for adjusting the clustering quota to a predetermined range. The invention further provides an intelligent auditing device and equipment based on the business travel quota, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of big data technology, and more specifically to intelligent review and intelligent recommendation methods, devices, equipment, media and program products based on travel allowances. Background Art

[0002] At present, banks and other companies usually manage employees' travel expenses by reimbursing them afterwards. When employees go on business trips, they choose the places where they spend money, and the merchants provide invoices based on the actual amount of money spent by the employees. Finally, the company reimburses the employees based on the amount of the invoices provided.

[0003] In order to avoid extravagance and waste, companies usually set various reimbursement limits to set values, for example, lunch reimbursement limit is 30 yuan. This method can meet some travel needs, but in some cases, there is a phenomenon of insufficient reimbursement limit. For example, for business trips to financial centers in developed cities, business trips to tourist attractions, and business trips to plateau cities, because the overall consumption level of the destination is high, the set value set by the company cannot match the consumption level of the place, resulting in insufficient reimbursement limit. In the case of insufficient reimbursement limit, the company usually handles it in the following way: employees apply for an increase in reimbursement limit during or after the event, and the company managers approve the application. This processing flow is manpower-consuming; secondly, the decision-making of company managers lacks data support, and approval is based on subjective judgment, which lacks reliability and scientificity. Summary of the invention

[0004] In view of the above problems, the present disclosure provides intelligent review and intelligent recommendation methods, devices, equipment, media and program products based on travel allowances.

[0005] According to a first aspect of the present disclosure, there is provided an intelligent audit method based on travel credit, comprising: obtaining a user level of a user, and determining an initial credit according to the user level; auditing the user's data to be reimbursed based on the initial credit; in response to the data to be reimbursed being greater than the initial credit, clustering a data set containing consumption data of multiple objects through a clustering algorithm, and obtaining multiple consumption data unit prices, wherein the consumption data of the multiple objects and the data to be reimbursed are all consumption data generated by the same type of merchants within a predetermined address range; and determining a cluster credit according to the multiple consumption data unit prices and a first floating parameter, and auditing the data to be reimbursed based on the cluster credit, wherein the first floating parameter is used to adjust the cluster credit to a predetermined range.

[0006] According to an embodiment of the present disclosure, a data set containing consumption data of multiple objects is clustered by a clustering algorithm to obtain multiple unit prices of consumption data, including: obtaining relevant consumption data corresponding to the data to be reimbursed based on a big data platform, wherein the relevant consumption data and the data to be reimbursed are both consumption data generated by the same type of merchants within a predetermined address range; filtering the relevant consumption data to obtain a data set containing consumption data of multiple objects; clustering the consumption data in the data set by time periods by a clustering algorithm; and taking the minimum value among the data values ​​of each cluster center as the multiple unit prices of consumption data.

[0007] According to an embodiment of the present disclosure, the clustering algorithm includes a K-means++ clustering algorithm.

[0008] According to an embodiment of the present disclosure, obtaining relevant consumption data corresponding to the data to be reimbursed based on the big data platform includes: obtaining relevant consumption data of different time periods corresponding to the data to be reimbursed.

[0009] According to an embodiment of the present disclosure, clustering the consumption data in the data set by time periods using a clustering algorithm includes: clustering the consumption data corresponding to different time periods in the data set, and obtaining cluster center data values ​​corresponding to each time period.

[0010] According to an embodiment of the present disclosure, taking the minimum value among the cluster center data values ​​as the multiple consumption data unit prices includes: taking the minimum value among the cluster center data values ​​corresponding to different time periods as the multiple consumption data unit prices.

[0011] A second aspect of the present disclosure provides an intelligent recommendation method based on travel quota, including: obtaining a user's target location, determining multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type; clustering a data set containing consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects are consumption data generated by multiple targets; determining multiple recommended quotas based on the multiple consumption data unit prices and multiple floating parameters, wherein the number of the multiple recommended quotas and the number of the multiple floating parameters are the same as the number of the multiple consumption data unit prices, and the multiple floating parameters are used to adjust the recommended quota corresponding to each floating parameter to a predetermined range; and determining multiple to-be-recommended targets corresponding to each recommended quota from the multiple targets based on the multiple recommended quotas, and recommending the multiple to-be-recommended targets corresponding to each recommended quota to the user respectively.

[0012] According to an embodiment of the present disclosure, clustering a data set containing consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices includes: clustering the data set containing consumption data of multiple objects according to different time periods through a clustering algorithm to obtain the consumption data unit price corresponding to each time period.

[0013] The third aspect of the present disclosure provides an intelligent audit device based on travel quota, including: an acquisition module, used to obtain the user level of a user, and determine the initial quota according to the user level; an audit module, used to audit the user's data to be reimbursed based on the initial quota; a clustering module, used to cluster a data set containing consumption data of multiple objects through a clustering algorithm in response to the data to be reimbursed being greater than the initial quota, and obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects and the data to be reimbursed are all consumption data generated by the same type of merchants within a predetermined address range; and the audit module is also used to: determine the clustering quota according to the multiple consumption data unit prices and a first floating parameter, and audit the data to be reimbursed based on the clustering quota, wherein the first floating parameter is used to adjust the clustering quota to a predetermined range.

[0014] The fourth aspect of the present disclosure provides an intelligent recommendation device based on travel quota, including: an acquisition module, used to acquire the user's target location, and determine multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type; a clustering module, used to cluster a data set containing consumption data of multiple objects through a clustering algorithm, and obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects are consumption data generated by multiple targets; a determination module, used to determine multiple recommended quotas based on the multiple consumption data unit prices and multiple floating parameters, wherein the number of the multiple recommended quotas and the number of the multiple floating parameters are the same as the number of the multiple consumption data unit prices, and the multiple floating parameters are used to adjust the recommended quota corresponding to each floating parameter to a predetermined range; and a recommendation module, used to determine multiple to-be-recommended targets corresponding to each recommended quota from the multiple targets based on the multiple recommended quotas, and recommend the multiple to-be-recommended targets corresponding to each recommended quota to the user respectively.

[0015] A fifth aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0016] The sixth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0017] The seventh aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1 The application scenario diagram of the intelligent review and intelligent recommendation method, device, equipment, medium and program product based on the travel quota according to the embodiment of the present disclosure is schematically shown;

[0020] Figure 2 A flowchart of an intelligent review method based on travel quota according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 3 A flowchart of a method for obtaining unit prices of multiple consumption data by using a clustering algorithm according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 4 A flowchart of an intelligent execution strategy according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 5 A flowchart of an intelligent recommendation method based on travel quota according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 6 A flowchart of an intelligent decision-making strategy according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 7 The structure block diagram of the intelligent audit device based on travel quota according to the embodiment of the present disclosure is schematically shown;

[0026] Figure 8 A schematic diagram of a structure of an intelligent recommendation device based on travel quota according to an embodiment of the present disclosure is shown; and

[0027] Fig. 9 A block diagram of an electronic device suitable for implementing an intelligent review and intelligent recommendation method based on travel quota according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0031] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0032] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user consumption information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0034] In view of the need for enterprises to carry out refined management of employee reimbursement amounts during business trips, in line with the goal of avoiding extravagance and waste while fully protecting the legitimate rights and interests of employees, the embodiments of the present disclosure provide an efficient intelligent decision-making or execution system for situations where travel allowances need to be adjusted during the travel process.

[0035] An embodiment of the present disclosure provides an intelligent audit method based on travel credit, including: obtaining a user level of a user, and determining an initial credit according to the user level; auditing the user's data to be reimbursed based on the initial credit; in response to the data to be reimbursed being greater than the initial credit, clustering a data set containing consumption data of multiple objects through a clustering algorithm, and obtaining multiple consumption data unit prices, wherein the consumption data of the multiple objects and the data to be reimbursed are all consumption data generated by the same type of merchants within a predetermined address range; and determining a cluster credit according to the multiple consumption data unit prices and a first floating parameter, and auditing the data to be reimbursed based on the cluster credit, wherein the first floating parameter is used to adjust the cluster credit to a predetermined range.

[0036] An embodiment of the present disclosure also provides an intelligent recommendation method based on travel quota, including: obtaining a user's target location, determining multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type; clustering a data set containing consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects are consumption data generated by multiple targets; determining multiple recommended quotas based on the multiple consumption data unit prices and multiple floating parameters, wherein the number of the multiple recommended quotas and the number of the multiple floating parameters are the same as the number of the multiple consumption data unit prices, and the multiple floating parameters are used to adjust the recommended quota corresponding to each floating parameter to a predetermined range; and determining multiple to-be-recommended targets corresponding to each recommended quota from the multiple targets based on the multiple recommended quotas, and recommending the multiple to-be-recommended targets corresponding to each recommended quota to the user respectively.

[0037] The intelligent review and recommendation method based on travel allowance provided by the present invention provides data-supported auxiliary decision-making solutions or intelligent decision-making solutions for employee travel allowance management through big data technology and machine learning technology, thereby reducing human resource consumption, improving review efficiency, and enhancing the reliability and scientificity of decision-making.

[0038] It should be noted that the intelligent review and intelligent recommendation method and device based on travel allowance in the embodiments of the present disclosure can be used in the field of big data technology, and can also be used in any field except the field of big data technology. The present disclosure does not limit the application field of the intelligent review and intelligent recommendation method and device based on travel allowance.

[0039] Figure 1 The application scenario diagram of the intelligent review and intelligent recommendation method based on travel quota according to an embodiment of the present disclosure is schematically shown.

[0040] like Figure 1As shown, the application scenario 100 according to this embodiment may include a terminal device, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0041] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0042] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0043] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0044] It should be noted that the intelligent review and intelligent recommendation method based on the travel quota provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the intelligent review and intelligent recommendation device based on the travel quota provided in the embodiment of the present disclosure can generally be set in the server 105. The intelligent review and intelligent recommendation method based on the travel quota provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the intelligent review and intelligent recommendation device based on the travel quota provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0045] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0046] The following will be based on Figure 1 The scene described by Figure 2~Figure 6 The intelligent review and intelligent recommendation method based on travel allowance in the disclosed embodiment is described in detail.

[0047] Figure 2 The flowchart of the intelligent review method based on travel quota according to the embodiment of the present disclosure is schematically shown.

[0048] like Figure 2 As shown, the intelligent audit method 200 based on travel quota of this embodiment includes operations S210 to S240, and the intelligent audit method 200 can be executed by a terminal device.

[0049] In operation S210, the user level of the user is obtained, and an initial credit limit is determined according to the user level.

[0050] Usually, the company sets different travel expense standards for employees at different levels. Managers, team leaders, and ordinary employees have different travel expense standards. For example, the travel expense standard for managers is higher than that for ordinary employees. At the same time, the company sets various travel expense standards for employees at the same level, including catering standards, accommodation standards, travel standards, etc. You can set a corresponding initial limit for each type of travel expense standard, or you can set a total initial limit for consumption during the business trip. The specific initial limit can be set according to specific regulations.

[0051] In some embodiments, the initial amount that can be reimbursed for a user is determined based on the user level corresponding to the user. Specifically, the user level, as well as the dining standards, accommodation standards, travel standards, etc. corresponding to the level are comprehensively considered to determine the initial amount that can be reimbursed for the user. For example, the user is an ordinary employee and belongs to the first level. The dining standard is 100 yuan / day, and the accommodation standard is 300 yuan / day. For a two-day business trip, the user's initial dining amount is 200 yuan, and the initial accommodation amount is 600 yuan, with a total initial amount of 800 yuan.

[0052] In operation S220, the user's data to be reimbursed is reviewed based on the initial amount.

[0053] Based on the initial quota, the data to be reimbursed generated during the user's business trip is reviewed. The data to be reimbursed is the consumption data with invoices generated during the user's business trip. The catering consumption data in the reimbursement data can be reviewed based on the initial quota for catering, the accommodation consumption data in the reimbursement data can be reviewed based on the initial quota for accommodation, the travel consumption data in the reimbursement data can be reviewed based on the initial quota for travel, or all the data to be reimbursed can be reviewed based on the total initial quota.

[0054] Exemplarily, when the data to be reimbursed is less than or equal to the initial amount, the review is passed; when the data to be reimbursed is greater than the initial amount, the review is not passed. The review process can be executed by computer equipment, thereby reducing human resource consumption. For example, if the data to be reimbursed generated by an employee on a business trip is less than the initial amount specified by the company, the review is passed and the corresponding reimbursement amount is issued to the employee. Alternatively, the reimbursement data can be classified and reimbursed. For example, if the catering reimbursement data in the data to be reimbursed generated by an employee on a business trip is less than the initial catering amount specified by the company, the review is passed and the employee is issued the reimbursement amount corresponding to the catering reimbursement data.

[0055] In addition, a floating range and a floating parameter can be set for the initial amount, and the employee's data to be reimbursed can be reviewed based on the floating parameter and the initial amount. For example, when the employee's data to be reimbursed is less than the sum of the initial amount and the floating parameter, the review is passed and the employee is issued a reimbursement amount corresponding to the data to be reimbursed.

[0056] For the case where the data to be reimbursed is greater than the initial amount, the following description will refer to operation S230.

[0057] In operation S230, in response to the data to be reimbursed being greater than the initial amount, a data set containing consumption data of multiple objects is clustered using a clustering algorithm to obtain multiple unit prices of consumption data, wherein the consumption data of the multiple objects and the data to be reimbursed are all consumption data generated by the same type of merchants within a predetermined address range.

[0058] In some embodiments, if the amount of data to be reimbursed is greater than the initial amount, consumption data generated by merchants of the same type as the data to be reimbursed within the predetermined address range can be referenced. Specifically, for reimbursed dining data, consumption data generated by multiple restaurants within the predetermined range of the user's dining location can be referenced; for reimbursed accommodation data, consumption data generated by multiple hotels within the predetermined range of the user's hotel can be referenced; for reimbursed travel data, consumption data of multiple trips within the predetermined range of the user's activity location can be referenced.

[0059] The predetermined address range is a range expanded based on the address where the user generates the data to be reimbursed, for example, a range within a predetermined distance from the address where the user generates the data to be reimbursed, or a range within a predetermined walking time from the address where the user generates the data to be reimbursed. Selecting the consumption data of multiple objects of the same type of merchants within the predetermined address range as a clustered data set can reflect the consumption level of this type of consumption within the predetermined address range, thereby providing data support for reviewing the user's data to be reimbursed and improving the scientific nature of the review.

[0060] For example, based on the location where the employee consumes, similar consumption places near the location are obtained, and the consumption data of multiple objects in the same type of consumption places are used as the clustered data set. Taking catering consumption as an example, based on the restaurant where the employee’s meal is billed, the consumption data of multiple restaurants within a 10-minute walk from the restaurant are obtained as the clustered data set. The restaurant search function and walking time calculation function of location-based service software or commercial map software can be used to calculate the restaurants within x minutes of walking distance from the billing restaurant. The specific search range can be set according to the actual situation and will not be elaborated in detail here.

[0061] In some embodiments, a data set containing consumption data of multiple objects is clustered by a clustering algorithm to obtain multiple unit prices of consumption data. The clustering algorithm here can be any algorithm that can cluster a data set, for example, K-means clustering, hierarchical clustering, density clustering, etc. The data set can be divided into multiple classes by a clustering algorithm, each class includes a corresponding cluster center, and the unit price of consumption data can be determined according to the cluster center. Specifically, the data set can be divided into several major classes first, and each major class is clustered separately, and the minimum value in the cluster center of each major class is used as the unit price of consumption data, thereby obtaining multiple unit prices of consumption data corresponding to the several major classes.

[0062] In some embodiments, the clustering algorithm includes a K-means++ clustering algorithm. The K-means++ clustering algorithm is used to cluster a data set containing consumption data of multiple objects to obtain multiple consumption data unit prices. Figure 3 A detailed description is given of how to obtain multiple consumption data unit prices through the K-means++ clustering algorithm.

[0063] In operation S240, a clustering quota is determined according to a plurality of consumption data unit prices and a first floating parameter, and the data to be reimbursed is reviewed based on the clustering quota, wherein the first floating parameter is used to adjust the clustering quota to a predetermined range.

[0064] The first floating parameter may be a preset parameter used to adjust the clustering quota to a predetermined range. Specifically, after obtaining multiple consumption data unit prices, an initial clustering quota is obtained according to the multiple consumption data unit prices, and the first floating parameter may indicate further adjustment based on the initial clustering quota to obtain the final clustering quota.

[0065] The first floating parameter can adjust the initial clustering quotas corresponding to multiple consumption unit prices. Specifically, for catering reimbursement, the multiple consumption unit prices include breakfast consumption unit price, lunch consumption unit price, and dinner consumption unit price. For example, the initial clustering quota corresponding to breakfast is determined based on the breakfast consumption unit price. The first floating parameter adjusts the initial clustering quota to obtain the clustering quota corresponding to breakfast.

[0066] The first floating parameter can also adjust the initial clustering quota determined by multiple consumption unit prices. For example, the initial clustering quota can be obtained by summing up multiple consumption data unit prices. On the basis of the initial clustering quota, a preset value can be increased or decreased, and the increased or decreased initial clustering quota can be used as the final clustering quota, wherein increasing the preset value or decreasing the preset value is the first floating parameter.

[0067] In some embodiments, the reimbursement data is reviewed based on the clustering quota. The clustering quota utilizes multiple unit prices of consumption data obtained through the clustering algorithm. That is to say, the clustering quota takes into account the consumption data of the same type of merchants within a predetermined range near the user's consumption address. The multiple unit prices of consumption data obtained through the clustering algorithm reflect the consumption level within a predetermined range near the user's consumption address. Reviewing the reimbursement data based on the clustering quota is equivalent to reviewing the reimbursement data according to the consumption level near the user's consumption address. Therefore, it provides data support for the review of the data to be reimbursed, ensuring the scientificity, rigor and rationality of the review.

[0068] The intelligent audit method based on travel quota in the disclosed embodiment intelligently determines the initial quota and cluster quota, reduces human resource consumption and reduces audit costs; automatically increases the cluster quota based on the unit price of consumption data and floating parameters, reduces the audit workload and improves audit efficiency; uses a data set containing consumption data of multiple objects to obtain the unit price of consumption data, provides data support for determining the cluster quota, thereby avoiding inaccuracies caused by subjective judgment of auditors and improving the scientific nature of the audit.

[0069] Figure 3 The flowchart of the method for obtaining unit prices of multiple consumption data by using a clustering algorithm according to an embodiment of the present disclosure is schematically shown.

[0070] like Figure 3As shown, the method 300 for obtaining multiple consumption data unit prices in this embodiment includes operations S310 to S340.

[0071] In operation S310, relevant consumption data corresponding to the data to be reimbursed is acquired based on the big data platform, wherein the relevant consumption data and the data to be reimbursed are both consumption data generated by merchants of the same type within a predetermined address range.

[0072] The big data platform contains a large amount of flow data. For example, banks have a large amount of collection data and payment data, and a large number of employees often travel on business, so there are relevant needs and implementation conditions. In the technical solution disclosed in this disclosure, the user information and data involved are all authorized by the user or fully authorized by all parties, and the collection, use, and application of relevant data are in compliance with relevant laws, regulations and standards, and necessary confidentiality measures are taken, which do not violate public order and good customs, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0073] Here, the relevant consumption data corresponding to the data to be reimbursed is also consumption data generated by the same type of merchants within the predetermined address range corresponding to the data to be reimbursed, but the range of the relevant consumption data is larger than the above-mentioned data set containing consumption data of multiple objects. The above-mentioned data set is data obtained based on the relevant consumption data corresponding to the data to be reimbursed. In the following, reference will be made to operation S320 to describe the data set of consumption data containing multiple objects obtained based on the relevant consumption data.

[0074] In some embodiments, obtaining relevant consumption data corresponding to the data to be reimbursed based on the big data platform includes: obtaining relevant consumption data of different time periods corresponding to the data to be reimbursed.

[0075] For the same consumption type, the consumption amounts in different time periods may vary greatly. Therefore, relevant consumption data corresponding to different time periods may be obtained, and subsequent operations may be performed on the relevant consumption data corresponding to different time periods. For example, for catering consumption, the relevant consumption data in different time periods include breakfast consumption data, lunch consumption data, and dinner consumption data. The following operations S320 are performed on the breakfast consumption data, lunch consumption data, and dinner consumption data, respectively.

[0076] In operation S320, relevant consumption data is filtered to obtain a data set including consumption data of multiple objects.

[0077] Filtering relevant consumption data includes filtering out some special cases such as small consumption data, and filtering out consumption data that is not related to the specified consumption content, so that the obtained data set can better reflect the consumption level within the predetermined address range corresponding to the data to be reimbursed, and provide data support for intelligent auditing. Specifically, for catering consumption data, filter out consumption data that is not related to breakfast, lunch, and dinner. For example, customers may buy the main meal first and then the beverage, or buy a takeaway box after checking out, etc., resulting in multiple payment records. Therefore, it is necessary to summarize the amount paid for each payment ID according to the payment ID (for example, the customer card number), and set a minimum threshold amount to exclude special cases such as customers only buying a bottle of mineral water, a pack of paper towels, and other small payments, and only retain payment records close to real meals. Similarly, for accommodation consumption data, filter out consumption data that is not related to accommodation fees; for travel consumption data, filter out consumption data that is not related to the fare to the destination.

[0078] Exemplarily, filtering relevant consumption data includes: filtering consumption data corresponding to different time periods separately. For example, relevant consumption data corresponding to lunch is usually greater than relevant consumption data corresponding to breakfast. Therefore, a lower threshold amount is set for the lunch period to filter the relevant consumption data of this period, and a lower threshold amount is set for the breakfast period to filter the relevant consumption data of this period.

[0079] The embodiments of the present disclosure can filter the relevant consumption data to: reduce the amount of data, avoid the response clustering effect of special data, irrelevant data, etc., improve the accuracy of the unit price of the acquired consumption data; and improve the calculation efficiency.

[0080] In operation S330, the consumption data in the data set is clustered by time periods using a clustering algorithm.

[0081] Clustering the consumption data in the data set by time periods by using a clustering algorithm includes: clustering the consumption data corresponding to different time periods in the data set, and obtaining a cluster center data value corresponding to each time period.

[0082] Different time periods correspond to different consumption content, different consumption habits, and different merchant rules. Clustering by time period can obtain more reasonable unit prices of consumption data, improve the scientific nature of subsequent audits, and thus improve the quality of audits.

[0083] In some embodiments, the consumption data corresponding to different time periods in the data set are clustered respectively using the K-means++ clustering algorithm.

[0084] Taking the dataset of consumption data including multiple objects as an example of catering consumption data, the catering consumption data is divided into breakfast consumption data, lunch consumption data, and dinner consumption data, and clustering is performed for each time period separately. Users' dining in restaurants is pre-divided into four scenarios: "dining alone", "dining for two", "dining for three", and "dining for four or more people", that is, the data partitioning method is determined. Since the number of clusters to be partitioned (i.e., the K value) has been determined in advance, when the number of clusters K is determined, the K-means++ clustering algorithm is simple, efficient, and suitable for large-scale data mining. Compared with the K-means algorithm, the K-means++ clustering algorithm improves the disadvantage that the mutual distance between the selected initial clustering centers is relatively close.

[0085] Given a dataset including n objects, the K-means++ clustering algorithm can construct K partitions of the dataset, and each partition is a cluster, satisfying the conditions:

[0086] (1)K < n;

[0087] (2)Each cluster has at least one piece of data;

[0088] (3)Each piece of data belongs to only one cluster;

[0089] When constructing the K clusters of the dataset, the similarity or correlation of the data in each cluster should be as high as possible, and the similarity or correlation of the data between different clusters should be as low as possible. Therefore, the mean square error should be minimized, as shown in Formula 1:

[0090] (1)

[0091] Where, represents the j-th piece of data, represents the -th clustering center, represents the data set, and K represents the number of clusters to be partitioned.

[0092] The specific steps of the K-means++ clustering algorithm are as follows:

[0093] Input: A dataset including n objects, the number of clusters k to be partitioned.

[0094] Step 1: Randomly select m (m < k) pieces of data as clustering centers.

[0095] Step 2: When selecting the next clustering center, the points farther away from the already selected clustering centers have a higher probability of being selected as the next clustering center.

[0096] Step 3: Repeat Step 2 until k clustering centers are selected.

[0097] Step 4: Assign each remaining data piece to the cluster closest to the cluster center.

[0098] Step 5: For each assigned cluster, calculate the new cluster center.

[0099] Step 6: Repeat steps 4 and 5 until all data are assigned to clusters and the cluster centers are no longer updated.

[0100] Finally, we get 4 clusters and corresponding cluster centers. The cluster centers represent the corresponding unit prices of the clusters. For example, the 4 cluster centers represent the corresponding unit prices of “dining for 1 person”, “dining for 2 people”, “dining for 3 people” and “dining for 4 or more people” from small to large.

[0101] Exemplarily, by clustering the consumption data corresponding to different time periods respectively, a plurality of cluster centers corresponding to each time period can be obtained.

[0102] In operation S340, the minimum value among the cluster center data values ​​is used as a plurality of consumption data unit prices.

[0103] Specifically, taking the minimum value among the cluster center data values ​​as the multiple consumption data unit prices includes: taking the minimum value among the cluster center data values ​​corresponding to different time periods as the multiple consumption data unit prices.

[0104] In some embodiments, the consumption data in the data set corresponds to different time periods, and the minimum value of the cluster center corresponding to each time period is used as the unit price of the consumption data, and multiple unit prices of consumption data can be obtained. For example, the minimum value of the cluster center corresponding to the breakfast time period, the lunch time period, and the dinner time period is used as the unit price of breakfast consumption data, the unit price of lunch consumption data, and the unit price of dinner consumption data, respectively. The embodiment of the present disclosure determines the clustering quota based on multiple unit prices of consumption data and the first floating parameter, and audits the data to be reimbursed based on the clustering quota, thereby realizing intelligent audit of the data to be reimbursed and avoiding human resource consumption.

[0105] The above operations S310 to S340 achieve clustering of a data set containing consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices. The multiple consumption data unit prices obtained through the clustering algorithm provide data support for intelligent auditing and improve the reliability of the audit. Clustering a data set containing consumption data of multiple objects by time period improves the accuracy and quality of the obtained consumption data unit prices, helps improve the audit quality, and realizes the refined management of travel quotas.

[0106] Figure 4 The flowchart of the intelligent execution strategy according to the embodiment of the present disclosure is schematically shown.

[0107] Usually, companies set different travel expense standards for employees at different job levels. Therefore, when implementing intelligent execution strategies, you need to enter the employee's job level. In addition, companies set a floating range for employees' travel allowances, so you need to enter the corresponding floating parameters.

[0108] like Figure 4 As shown, the intelligent execution strategy process is as follows: Enter the employee's position level G and the first floating parameter , determine the employee's initial quota G0 based on the job level, and approve it when the employee's data to be reimbursed sum is less than or equal to the initial quota; otherwise, calculate the consumption data unit prices x, y, and z in different time periods of the data set containing consumption data of multiple objects corresponding to the data to be reimbursed through a clustering algorithm (for example, the breakfast consumption data unit price x, the lunch consumption data unit price y, and the dinner consumption data unit price z), and calculate the sum SUM of x, y, and z (for example, the sum of the employee's dining unit price), based on the first floating parameter Adjust SUM to determine whether sum is less than or equal to SUM and If yes, it will be approved directly, otherwise it will be manually reviewed. The review manager can further review the employee's data to be reimbursed by referring to the calculated unit price of consumption data (for example, the unit price of restaurant meals).

[0109] Exemplarily, the intelligent execution strategy of the embodiment of the present disclosure may be implemented as an application program, and the application program may be installed on a terminal device.

[0110] The intelligent audit method based on travel quota provided by the embodiment of the present disclosure uses a clustering algorithm to cluster a data set containing consumption data of multiple objects when the data to be reimbursed is greater than the initial quota, obtains multiple unit prices of consumption data, determines the clustering quota based on the multiple unit prices of consumption data and the first floating parameter, and audits the data to be reimbursed based on the clustering quota. The method provides data support for the audit of the data to be reimbursed, improves the accuracy and scientificity of the audit, reduces manpower consumption, and improves audit efficiency.

[0111] In some embodiments, in order to achieve lower management costs, you can consider using an intelligent recommendation solution. Relevant managers preset consumption venue screening strategies in advance, and recommend suitable consumption venues to employees through office software when employees are on business trips. For example, for employees' breakfast, lunch, and dinner during business trips, they can intelligently recommend restaurants to employees and automatically increase their travel allowances.

[0112] Figure 5 The flowchart of the intelligent recommendation method based on travel quota according to an embodiment of the present disclosure is schematically shown.

[0113] like Figure 5As shown, the intelligent recommendation method 500 based on travel quota of this embodiment includes operations S510 to S540, and the intelligent recommendation method 500 can be executed by a terminal device.

[0114] In operation S510, a target location of a user is acquired, and a plurality of targets within a predetermined range are determined based on the target location, wherein the plurality of targets are merchants of the same type.

[0115] The target location is a specific location in the user's travel destination. For example, the target location can be the user's meeting place, the area where the user will stay, the airport or station where the user arrives, etc. Determining multiple targets within a predetermined range based on the target location includes: taking the same type of merchants whose distance from the target location is less than or equal to the preset distance as multiple targets; or taking the same type of merchants whose walking time (or ride time) from the target location is less than or equal to the preset time as multiple targets. The method of determining multiple targets within a predetermined range is not limited to the above method, and multiple targets within a predetermined range can be determined according to actual requirements, for example, by comprehensively considering distance factors and time factors to determine multiple targets within a predetermined range.

[0116] In operation S520, a data set including consumption data of multiple objects is clustered by a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects is consumption data generated by multiple targets.

[0117] The consumption data generated by multiple targets are the consumption data generated by merchants of the same type, for example, the consumption data of multiple catering merchants within two kilometers of the user's business trip location.

[0118] In some embodiments, clustering a data set containing consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices includes: clustering the data set containing consumption data of multiple objects according to different time periods through a clustering algorithm to obtain the consumption data unit price corresponding to each time period.

[0119] Different time periods correspond to different consumption content, different consumption habits, and different merchant rules. Clustering by time period can obtain more reasonable unit prices of consumption data, improve the accuracy and scientificity of subsequent recommendations, and improve the quality of recommendations.

[0120] The specific steps of clustering the data set containing the consumption data of multiple objects by a clustering algorithm and obtaining the unit prices of multiple consumption data can refer to the above-mentioned operations S230, S330, S340, etc., which will not be elaborated in detail here. The clustering algorithm here can be K-means++ clustering.

[0121] In operation S530, multiple recommended amounts are determined based on multiple consumption data unit prices and multiple floating parameters, wherein the number of the multiple recommended amounts, the number of the multiple floating parameters and the number of the multiple consumption data unit prices are the same, and the multiple floating parameters are used to adjust the recommended amount corresponding to each floating parameter to a predetermined range.

[0122] In some embodiments, the values ​​of multiple floating parameters may be the same or different, and the values ​​of the floating parameters may be set according to the characteristics of consumption data in different time periods. For example, a larger floating parameter may be set for the unit price of lunch consumption data and the unit price of dinner consumption data. Furthermore, according to some corporate travel management regulations, when making intelligent recommendations, floating parameters may not be set or floating parameters may be set for part of the travel quota. In this case, some of the multiple floating parameters in the disclosed embodiment may be set to zero.

[0123] A clustering algorithm is used to obtain multiple unit prices of consumption data within a predetermined range of the target location, and each unit price of consumption data is adjusted by a floating parameter to obtain the recommended amount corresponding to the unit price of consumption data. Multiple unit prices of consumption data correspond to different time periods, so the recommended amount corresponding to each time period can be obtained. For example, the recommended amount corresponding to breakfast is the sum of the unit price of breakfast consumption data and the corresponding floating parameter.

[0124] In operation S540, a plurality of to-be-recommended targets corresponding to each recommended amount are determined from the plurality of targets based on the plurality of recommended amounts, and the plurality of to-be-recommended targets corresponding to each recommended amount are respectively recommended to the user.

[0125] After determining multiple recommended amounts corresponding to multiple consumption data unit prices, multiple targets to be recommended corresponding to each recommended amount are screened from multiple targets. Specifically, for a time period, among multiple targets, if the consumption data unit price of a single target itself (i.e., the average customer price of the merchant) is less than or equal to the recommended amount corresponding to the time period, the single target is used as the corresponding target to be recommended.

[0126] The intelligent recommendation method based on travel quota in the disclosed embodiment can reduce management costs and human resource consumption by intelligently screening merchants in advance and recommending them to users; automatically adjusting the recommended quota can improve work efficiency; setting corresponding recommended quotas for multiple consumption data unit prices can improve the accuracy and scientificity of recommendations and improve the quality of recommendations.

[0127] Figure 6 The flowchart of the intelligent decision-making strategy according to the embodiment of the present disclosure is schematically shown.

[0128] The intelligent decision-making strategy of this embodiment obtains multiple targets within a predetermined range of the target location through map software or location-based service technology, and recommends multiple recommended targets with average customer spending within a recommended amount to employees.

[0129] like Figure 6 As shown in the figure, taking the example of recommending restaurants to employees on business trips, arrays T, R, and L are used to store restaurant names, y[r], ly[r] represent the average customer spending of restaurant r, , is the adjustment factor, N is the minimum number of restaurants selected by location-based service technology or map software, Y is the number of recommended restaurants, and Z is the preset amount of travel reimbursement (for example, the recommended amount). The intelligent decision-making strategy process is as follows: Input Y, , , N, select n restaurants within X minutes’ walk from the target location through location-based service technology or map software. If n is less than N, adjust the factor Increase the walking time X until the number of restaurants n is greater than or equal to N. When t is less than Y and r is less than n, the restaurant's average customer spending y[r] is less than or equal to the preset amount Z, then the restaurant is stored in array T; otherwise, the restaurant is stored in a temporary array L, and the restaurant's average customer spending is stored in a temporary array ly. When r is equal to n, increase the preset amount Z by adjusting the factor β and continue to judge until Y qualified recommended restaurants are obtained, output array T (Y recommended restaurants), and end the loop.

[0130] Exemplarily, the intelligent decision-making strategy of the embodiment of the present disclosure may be implemented as an application program, and the application program may be installed on a terminal device.

[0131] Based on the above-mentioned intelligent audit method based on travel quota, the present disclosure also provides an intelligent audit device based on travel quota. Figure 7 The device is described in detail.

[0132] Figure 7 The structural block diagram of the intelligent audit device based on travel quota according to an embodiment of the present disclosure is schematically shown.

[0133] like Figure 7 As shown, the intelligent audit device 700 based on travel quota of this embodiment includes an acquisition module 710 , an audit module 720 and a clustering module 730 .

[0134] The acquisition module 710 is used to acquire the user level of the user and determine the initial credit limit according to the user level. In one embodiment, the acquisition module 710 can be used to perform the operation S210 described above, which will not be repeated here.

[0135] The review module 720 is used to review the user's to-be-reimbursed data based on the initial amount. In one embodiment, the review module 720 can be used to perform the operation S220 described above, which will not be described in detail here.

[0136] The clustering module 730 is used to cluster a data set containing consumption data of multiple objects through a clustering algorithm in response to the data to be reimbursed being greater than the initial amount, and obtain multiple unit prices of consumption data, wherein the consumption data of the multiple objects and the data to be reimbursed are all consumption data generated by the same type of merchants within a predetermined address range; in one embodiment, the clustering module 730 can be used to execute the operation S230 described above, which will not be repeated here.

[0137] The audit module 720 is also used to determine the clustering quota according to the unit prices of the plurality of consumption data and the first floating parameter, and to audit the reimbursement data based on the clustering quota, wherein the first floating parameter is used to adjust the clustering quota to a predetermined range. In one embodiment, the acquisition module 720 can be used to perform the operation S240 described above, which will not be described in detail here.

[0138] Based on the above-mentioned intelligent recommendation method based on travel quota, the present disclosure also provides an intelligent recommendation device based on travel quota. Figure 8 The device is described in detail.

[0139] Figure 8 The structural block diagram of the intelligent recommendation device based on travel quota according to an embodiment of the present disclosure is schematically shown.

[0140] like Figure 8 As shown, the travel quota-based intelligent recommendation device 800 of this embodiment includes an acquisition module 810 , a clustering module 820 , a determination module 830 and a recommendation module 840 .

[0141] The acquisition module 810 is used to acquire the user's target location, and determine multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type. In one embodiment, the acquisition module 810 can be used to perform the operation S510 described above, which will not be repeated here.

[0142] The clustering module 820 is used to cluster the data set containing the consumption data of multiple objects through a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects is the consumption data generated by multiple targets. In one embodiment, the clustering module 820 can be used to perform the operation S520 described above, which will not be repeated here.

[0143] The determination module 830 is used to determine multiple recommended quotas according to multiple consumption data unit prices and multiple floating parameters, wherein the number of the multiple recommended quotas and the number of the multiple floating parameters are the same as the number of the multiple consumption data unit prices, and the multiple floating parameters are used to adjust the recommended quota corresponding to each floating parameter to a predetermined range. In one embodiment, the determination module 830 can be used to perform the operation S530 described above, which will not be repeated here.

[0144] The recommendation module 840 is used to determine multiple to-be-recommended targets corresponding to each recommendation amount from multiple targets based on multiple recommendation amounts, and recommend the multiple to-be-recommended targets corresponding to each recommendation amount to the user. In one embodiment, the recommendation module 840 can be used to perform the operation S540 described above, which will not be repeated here.

[0145] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 810, the clustering module 820, the determination module 830 and the recommendation module 840 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 810, the clustering module 820, the determination module 830 and the recommendation module 840 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the acquisition module 810 , the clustering module 820 , the determination module 830 , and the recommendation module 840 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0146] Fig. 9 A block diagram of an electronic device suitable for implementing an intelligent review and intelligent recommendation method based on travel quota according to an embodiment of the present disclosure is schematically shown.

[0147] like Fig. 9As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0148] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0149] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the input / output (I / O) interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0150] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0151] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0152] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program includes a program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the intelligent review and intelligent recommendation method based on travel quota provided in the embodiment of the present disclosure.

[0153] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0154] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0155] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0156] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0157] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0158] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0159] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An intelligent audit method based on travel quota, characterized in that: The method comprises: Obtain the user level of the user and determine the initial credit limit based on the user level; Reviewing the user's data to be reimbursed based on the initial amount; In response to the data to be reimbursed being greater than the initial amount, clustering a data set containing consumption data of a plurality of objects by a clustering algorithm to obtain a plurality of unit prices of consumption data, wherein the consumption data of the plurality of objects and the data to be reimbursed are both consumption data generated by merchants of the same type within a predetermined address range; and A clustering quota is determined according to the unit prices of the multiple consumption data and a first floating parameter, and the data to be reimbursed is reviewed based on the clustering quota, wherein the first floating parameter is used to adjust the clustering quota to a predetermined range.

2. The method according to claim 1, characterized in that The step of clustering a data set containing consumption data of multiple objects by using a clustering algorithm to obtain multiple consumption data unit prices includes: Acquire relevant consumption data corresponding to the data to be reimbursed based on the big data platform, wherein the relevant consumption data and the data to be reimbursed are both consumption data generated by merchants of the same type within a predetermined address range; Filter the relevant consumption data to obtain the data set containing the consumption data of the multiple objects; Clustering the consumption data in the data set by time periods using the clustering algorithm; and The minimum value among the data values ​​of each cluster center is used as the multiple consumption data unit prices.

3. The method according to claim 2, characterized in that The clustering algorithm includes a K-means++ clustering algorithm.

4. The method according to claim 2, characterized in that: The obtaining of relevant consumption data corresponding to the data to be reimbursed based on the big data platform includes: obtaining relevant consumption data of different time periods corresponding to the data to be reimbursed.

5. The method according to claim 4, characterized in that The clustering of the consumption data in the data set by time periods by using the clustering algorithm includes: The consumption data corresponding to the different time periods in the data set are clustered respectively to obtain the cluster center data value corresponding to each time period.

6. The method according to claim 5, characterized in that The method of using the minimum value among the data values ​​of each cluster center as the multiple consumption data unit prices includes: The minimum value among the cluster center data values ​​corresponding to the different time periods is used as the multiple consumption data unit prices.

7. An intelligent recommendation method based on travel quota, characterized in that: The method comprises: Acquire a target location of the user, and determine multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type; Clustering a data set containing consumption data of multiple objects by a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects is the consumption data generated by the multiple targets; Determining a plurality of recommended amounts according to the plurality of consumption data unit prices and a plurality of floating parameters, wherein the number of the plurality of recommended amounts, the number of the plurality of floating parameters and the number of the plurality of consumption data unit prices are the same, and the plurality of floating parameters are used to adjust the recommended amount corresponding to each floating parameter to a predetermined range; and Based on the multiple recommended amounts, multiple to-be-recommended targets corresponding to each recommended amount are determined from the multiple targets, and the multiple to-be-recommended targets corresponding to each recommended amount are respectively recommended to the user.

8. The method according to claim 7, characterized in that The step of clustering a data set containing consumption data of multiple objects by using a clustering algorithm to obtain multiple consumption data unit prices includes: The data set containing the consumption data of the multiple objects is clustered according to different time periods by using the clustering algorithm to obtain the unit price of the consumption data corresponding to each time period.

9. An intelligent audit device based on travel quota, characterized in that: The device comprises: The acquisition module is used to obtain the user level of the user and determine the initial credit limit according to the user level; An audit module, used to audit the user's to-be-reimbursed data based on the initial amount; a clustering module, configured to cluster a data set containing consumption data of a plurality of objects by a clustering algorithm in response to the data to be reimbursed being greater than the initial amount, and obtain a plurality of unit prices of consumption data, wherein the consumption data of the plurality of objects and the data to be reimbursed are both consumption data generated by merchants of the same type within a predetermined address range; and The audit module is also used to: determine a clustering quota based on the multiple consumption data unit prices and a first floating parameter, and audit the data to be reimbursed based on the clustering quota, wherein the first floating parameter is used to adjust the clustering quota to a predetermined range.

10. An intelligent recommendation device based on travel quota, characterized in that: The device comprises: An acquisition module, used to acquire a target location of a user, and determine multiple targets within a predetermined range based on the target location, wherein the multiple targets are merchants of the same type; A clustering module, used to cluster a data set containing consumption data of multiple objects by a clustering algorithm to obtain multiple consumption data unit prices, wherein the consumption data of the multiple objects is the consumption data generated by the multiple targets; a determination module, configured to determine a plurality of recommended amounts according to the plurality of consumption data unit prices and a plurality of floating parameters, wherein the number of the plurality of recommended amounts, the number of the plurality of floating parameters and the number of the plurality of consumption data unit prices are the same, and the plurality of floating parameters are used to adjust the recommended amount corresponding to each floating parameter to a predetermined range; and The recommendation module is used to determine a plurality of to-be-recommended targets corresponding to each recommended amount from the plurality of targets based on the plurality of recommended amounts, and recommend the plurality of to-be-recommended targets corresponding to each recommended amount to the user respectively.

11. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6 or 7 to 8.

12. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 or 7 to 8 are implemented.

13. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 or 7 to 8 are implemented.

Images