Order information processing method, device, storage medium and computer program product
By processing buried point data and order data and using graph algorithms to train gang identification models, identifying illegal gang accounts or equipment in shared business, the problem of gang order identification in shared business is solved, ensuring the normal operation and user experience of the business .
Patent Information
- Application Number
- CN202110236725.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-03
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2041-03-03
AI Technical Summary
In a shared business, how to accurately identify and restrict orders initiated by illegal shared accounts or shared devices to prevent damage to normal business experience.
By processing buried point data and order data, abnormal order information sets and gang identification results are generated, and gang identification results are trained using graph algorithms to identify and mark accounts and equipment that may belong to the same gang, thereby realizing orders for gang accounts or gang equipment. Accurate identification.
The identification accuracy rate of gang accounts or gang equipment orders has been improved, ensuring the normal operation of the business, and avoiding the adverse impact of illegal orders on user experience.
Smart Images

Figure CN112967105B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of data processing technology, and in particular, to a method, device, storage medium, and computer program product for processing order information. Background Art
[0002] The development of Internet technology has led to the emergence of more businesses, among which sharing business is a relatively popular business type.
[0003] For sharing businesses, the emergence of shared accounts or shared devices will seriously affect the business experience of normal accounts or normal devices. How to accurately identify and limit orders initiated by illegal shared accounts or shared devices has become an indispensable part of the development of sharing businesses. Summary of the invention
[0004] Embodiments of the present disclosure provide a method, device, storage medium, and computer program product for processing order information, which are used to identify orders from group accounts or group devices to ensure the normal operation of the business.
[0005] In one aspect, an embodiment of the present disclosure provides a method for processing order information, comprising:
[0006] Obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user;
[0007] Pre-process the historical order information set according to the tracking point data and order data to obtain the abnormal order information set and the group identification result of the abnormal order information set;
[0008] The abnormal order information set and the corresponding group identification results are used to train a pre-built group identification model based on a graph algorithm to obtain a trained group identification model.
[0009] On the other hand, an embodiment of the present disclosure provides a method for processing order information, including:
[0010] Acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity placed by each account to be identified on each device to be identified;
[0011] Using the trained group identification model to process the order information set to be identified, to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group;
[0012] The trained group identification model is obtained by processing the order information according to any of the above-mentioned methods.
[0013] In another aspect, an embodiment of the present disclosure provides an order information processing device, including:
[0014] A first acquisition module is used to obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user;
[0015] The first processing module is used to pre-process the historical order information set according to the buried point data and the order data to obtain the abnormal order information set and the group identification result of the abnormal order information set;
[0016] The training module is used to train a pre-built graph algorithm-based group identification model using the abnormal order information set and the corresponding group identification results to obtain a trained group identification model.
[0017] In another aspect, an embodiment of the present disclosure provides an order information processing device, including:
[0018] A second acquisition module is used to acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity of each account to be identified placed on each device to be identified;
[0019] A second processing module, configured to process the order information set to be identified using the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group;
[0020] The trained group identification model is obtained by processing the order information according to any of the above-mentioned methods.
[0021] In another aspect, an embodiment of the present disclosure provides an order information processing device, including: a memory and a processor;
[0022] The memory is used to store program instructions;
[0023] The processor is used to call the program instructions in the memory to execute the method as described in any of the above items.
[0024] On the other hand, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored; when the computer program is executed, the method described in any of the preceding items is implemented.
[0025] In a final aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in any of the preceding items when executed by a processor.
[0026] The order information processing method, device, storage medium and computer program product provided by the embodiments of the present disclosure can obtain an abnormal order information set and a corresponding group identification result by processing the buried data and the order data; then, the abnormal order information set and the corresponding group identification result are used to train the model to obtain a trained group identification model, and the trained group identification model can be used to process the order information set to be identified to obtain a group identification result; wherein, the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and the identification accuracy is high, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0028] Figure 1 It is a schematic diagram of the unlocking process in the prior art;
[0029] Figure 2 A schematic diagram of a network architecture on which the present disclosure is based;
[0030] Figure 3 It is a flowchart of a method for processing order information provided by this application;
[0031] Figure 4 It is a flowchart of another method for processing order information provided by the present application;
[0032] Figure 5 A structural block diagram of an order information processing device provided in an embodiment of the present disclosure;
[0033] Figure 6 A structural block diagram of another order information processing device provided in an embodiment of the present disclosure;
[0034] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure.
[0035] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0036] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0037] The development of Internet technology has led to the emergence of more businesses, among which sharing business is a relatively popular business type. Sharing business is a new and popular business type, and shared bicycles are a specific business form of sharing business.
[0038] In the shared bicycle business, the business platform will provide a number of bicycles and carry out corresponding operation and maintenance management. After the user completes the registration on the business platform, he can control the unlocking of the target bicycle by scanning and other methods and start using it; when the user triggers the locking of the target bicycle, the platform will generate a corresponding order for the user to view the order and make the order payment.
[0039] However, the emergence of an illegal platform called “Quan Neng Che” has gradually disrupted the normal development of the business. “Quan Neng Che” can be understood as a way for users to unlock and lock the target bicycles through shared accounts or shared devices.
[0040] Specifically, Figure 1 It is a schematic diagram of the unlocking process in the prior art, such as Figure 1 As shown, generally, the normal operation of a shared bicycle is based on its inherent business server 1. When in use, the user will initiate an unlocking request for the target bicycle to the business server 1 through the shared bicycle APP or shared bicycle applet, and the business server 1 will return the corresponding unlocking key to the shared bicycle APP or shared bicycle applet after receiving the request, so that the user can use the unlocking key to unlock the target bicycle.
[0041] The "all-round car" also has its own business service end 2, which will also provide users with the "all-round car" APP. When in use, the user will report the unlocking request of the target bicycle to the business service end 2 through the "all-round car" APP, and then the business service end 2 will disguise its own identity in an illegal way to disguise itself as a shared bicycle applet and forward the unlocking request to the business service end 1. At this time, the business service end 1 will think that the unlocking request is from the shared bicycle applet, and will process it normally to return the unlocking key to the business service end 2, and the business service end 2 will forward the unlocking key to the "all-round car" APP, so that the user can use the unlocking key to unlock the target bicycle.
[0042] In the process of illegal unlocking of the "all-round car", it is necessary to collect some normal users' account information or device information as the "all-round car" APP shared account or shared device, which is used to generate an unlocking request reported to the business server 1. These shared accounts or shared devices will be provided to a large number of users.
[0043] The emergence of "all-purpose bikes" has, on the one hand, led to the theft of normal users' account information or device information, posing a serious threat to their information security. On the other hand, the illegal unlocking service of "all-purpose bikes" will also affect the normal operation and maintenance of shared bicycle business.
[0044] Based on this, how to accurately identify and limit the accounts and devices that are unlocked through the "all-purpose car" has become an urgent problem that needs to be solved.
[0045] In response to the above problems, the inventors found that the accounts or devices in the unlocking requests initiated by the business service end of the "all-round car" all have a many-to-one relationship, that is, multiple accounts may initiate unlocking requests through the same device, or multiple devices may initiate unlocking requests through the same account; in addition, during the sending of these unlocking requests, the operation data on the shared bicycle APP or shared bicycle applet is missing. By identifying whether there is a many-to-one relationship between accounts and devices and whether the operation data is missing, it is possible to quickly determine which accounts or devices belong to shared accounts or shared devices, thereby facilitating the subsequent order management in the business.
[0046] In other words, the disclosed embodiment obtains an abnormal order information set and a corresponding group identification result by processing the buried data and the order data; then, the model is trained using the abnormal order information set and the corresponding group identification result to obtain a trained group identification model, and the trained group identification model can be used to process the order information set to be identified to obtain a group identification result; wherein, the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and having a high identification accuracy rate, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders.
[0047] The following is a detailed description of the technical solutions of the embodiments of the present disclosure and how the technical solutions of the present disclosure solve the above-mentioned technical problems with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the embodiments of the present disclosure will be described below in conjunction with the accompanying drawings.
[0048] refer to Figure 2 , Figure 2A schematic diagram of a network architecture based on the present disclosure is shown in FIG. Figure 2 The network architecture shown may specifically include a business service end 11 and a processing server 12 .
[0049] Among them, the business service end 11 specifically refers to Figure 1 The shared bicycle business service end in the service provider can receive the unlocking request initiated by the user, and provide the user with the corresponding unlocking key and order information based on the unlocking request. When the user completes the use of the bicycle, the business service end 11 will settle the order information.
[0050] The processing server 12 can specifically be an execution end that executes the order information processing method provided by the present disclosure. It interacts with the business service end 11 to obtain the order information and user-related information therein. The processing server 12 will also perform corresponding processing on the order information based on the processing method provided by the present disclosure, and the business service end 11 can use the processing result to identify and determine whether the order information is illegal.
[0051] It is known that the business service end 11 and the processing server 12 can be specifically integrated in the same cloud server cluster, and realize the interaction of data and information by establishing a communication connection.
[0052] Embodiment 1
[0053] Figure 3 This is a flowchart of a method for processing order information provided by this application, such as Figure 3 As shown, the method includes:
[0054] Step 101: Obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user.
[0055] Step 102: pre-process the historical order information set according to the tracking point data and the order data to obtain an abnormal order information set and a group identification result of the abnormal order information set.
[0056] Step 103: Use the abnormal order information set and the corresponding group identification results to train a pre-built group identification model based on a graph algorithm to obtain a trained group identification model.
[0057] It should be noted that the order information processing method provided by the present disclosure can be specifically applied to an order information processing device, and the processing device can be specifically set Figure 2 The processing server 12 is shown.
[0058] In a method for processing order information provided in an embodiment of the present disclosure, a group identification model based on a graph algorithm is used to identify whether the account or device in the order information is a group account or group device (i.e., the aforementioned shared account or shared device). In order for the model to achieve the processing goal, the model needs to be trained so that it can achieve the identification function. The embodiment provided in the present disclosure uses buried point data and order data to train the group identification model.
[0059] Specifically, first, the processing device first obtains a historical order information set, which includes at least the burial point data of each user and the order data of each user.
[0060] The historical order information set is obtained by cleaning the original historical order data and extracting preset fields. Data cleaning and extraction of preset fields can reduce data redundancy and improve computing efficiency.
[0061] The historical order information set refers to the information set of completed orders within a period of time, which is stored in the business server.
[0062] The historical order information set includes but is not limited to the following data: each user's tracking data and each user's order data. Among them, tracking data refers to user behavior data. In the present disclosure, it may specifically include the behavior data generated when the user triggers the unlock request, such as opening the APP or applet, clicking "Scan" to start the camera module, confirming the unlock, confirming the lock, clicking to pay, and other user behavior data; tracking data can be stored in the form of a data list, which generally includes different fields such as the user's account ID, operation type, tracking coordinates, etc.
[0063] Order data refers to the relevant data of orders generated by users using the shared bicycle service, such as order time, order number, account ID, device ID and other different fields.
[0064] Then, the processing device pre-processes the historical order information set according to the buried point data and the order data to obtain the abnormal order information set and the group identification result of the abnormal order information set.
[0065] Among them, the processing device pre-processes the historical order information set according to the tracking data and order data, and the process of obtaining the abnormal order information set can be understood as: data cleaning, screening and clustering of the historical order information set based on the tracking data and order data to obtain relevant information of abnormal orders associated with group devices or group accounts.
[0066] Optionally, in order to enable the model to accurately identify abnormal orders, the following steps 1021 to 1023 provide a specific implementation method for selecting an abnormal order information set from a historical order information set.
[0067] Step 1021: filter the order data of each user in the historical order information set according to the buried data to obtain multiple candidate order data;
[0068] Step 1022: construct an order information set based on the plurality of candidate order data, wherein the order information set is used to represent the correspondence between different accounts and different devices in each candidate order data;
[0069] Step 1023: According to the correspondence between the account and the device in the order information set, select the order data of the account or device with a multilateral correspondence from the order information set to generate the abnormal order information set.
[0070] Since the present disclosure is specifically aimed at the application scenario of "all-round bike", the inventors have found through research that since the buried data can reflect the user's behavior, the user behavior when the user uses the "all-round bike" service end to unlock the shared bicycle is different from the user behavior when the normal user uses the shared bicycle service end to unlock, and this difference will be reflected in the buried data. The difference in buried data can be used to screen the order data of each user in the historical order information set to obtain multiple candidate order data with abnormalities.
[0071] Furthermore, in order to further improve the training effect and make the model more accurate in identifying abnormal users, the buried data are the operation data of users performing operations on multiple key operation nodes; accordingly, when the order data of each user in the historical order information set is screened according to the buried data to obtain multiple candidate order data, the key operation node coverage rate corresponding to the buried data can be determined based on the operation data of the user performing operations on different key operation nodes in each buried data, and then, the buried data whose key operation node coverage rate is less than the first threshold is selected, and the order data of the user corresponding to the selected buried data is used as the candidate order data.
[0072] As mentioned above, the use of a shared bicycle generally includes several key operation nodes, such as opening the APP, clicking to scan, confirming to unlock, confirming to lock, and paying the order. The buried data can count the user's operation data at different key operation nodes and form a buried data list similar to {A1, A2, A3, A4, A5}.
[0073] If the user unlocks the car normally, corresponding operation data should be generated at each key operation node; conversely, if the user unlocks the car abnormally (i.e., uses the "all-purpose car" to unlock the car), the operation data at some key operation nodes (such as opening the APP, clicking and scanning, etc.) is missing. Using this feature, the ratio of the number of key operation nodes with operation data to the total number of key operation nodes can be calculated to obtain the key operation node coverage rate corresponding to the buried data. Then, according to the key operation node coverage rate, the buried data with a key operation node coverage rate less than the first threshold value may be the buried data generated by the user illegally unlocking the car through the "all-purpose car". At this time, the order data of the user in the historical order information set needs to be selected as candidate order data.
[0074] Optionally, the first threshold value may be set to 80%. Of course, the first threshold value may be set according to actual conditions.
[0075] Subsequently, after multiple candidate order data, the processing device will determine the order volume generated by the same account under the same device among the multiple candidate order data, and then generate the order information set based on the order volume generated by the same account under the same device.
[0076] For example, the order information set may include: [P1, D1, N1], [P2, D2, N1], [P1, D2, N2], [P1, D3, N1], [P3, D2, N3], [P3, D2, N3], and [P4, D4, N1]. P may be used to identify account P, D may be used to identify device D, and N may be used to indicate that the quantity of the order is N.
[0077] By generating an order information set, the corresponding relationship between accounts and devices can be better determined and analyzed.
[0078] That is to say, the processing device will also select abnormal accounts or abnormal devices with multilateral correspondence from the order information set.
[0079] Specifically, an abnormal account with a corresponding relationship on the opposite side refers to an account that generates orders under multiple devices (such as 3 devices) under the same account. For example, in the above example, account P1 corresponds to three devices: device D1, device D2, and device D3; account P2 corresponds to the only device D2; account P3 corresponds to the only device D2; and account P4 corresponds to the only device D4.
[0080] Through analysis, it can be known that "Almighty Bike" generally uses a shared account to send unlocking requests, that is, when different users perform unlocking operations through "Almighty Bike", "Almighty Bike" will use the same account to generate unlocking requests and send them to the shared bicycle service end to obtain multiple unlocking keys. Therefore, when it is determined that the same account corresponds to multiple devices, the account may be an abnormal account that uses "Almighty Bike", and the various devices involved may use related devices of "Almighty Bike", that is, the above-mentioned account P1 is an abnormal account, and its corresponding devices D1, D2 and D3 are its corresponding devices.
[0081] Similarly, an abnormal device with a multilateral correspondence refers to a device where multiple accounts (such as 3 accounts) generate order volumes under the same device; for example, in the above example, device D1 corresponds to account P1, device D2 corresponds to account P1, account P2 and account P3, device D3 corresponds to account P1, and device D4 corresponds to account P4.
[0082] Through analysis, it can be known that when a device using the "all-round car" uses the "all-round car" multiple times, it will use multiple accounts provided by the "all-round car". Therefore, when it is determined that the same device corresponds to multiple accounts, the device may be an abnormal device using the "all-round car", and the accounts involved may be related accounts of the "all-round car", that is, the above-mentioned device D2 is an abnormal device, and its corresponding accounts P1, P2 and P3 are its corresponding accounts.
[0083] Then, the processing device will use these abnormal accounts, their corresponding devices and order quantities, as well as these abnormal devices, their corresponding accounts and order quantities to generate the abnormal order information set.
[0084] That is, the abnormal order information set is obtained, [P1, D1, N1], [P2, D2, N1], [P1, D2, N2], [P1, D3, N1], [P3, D2, N3].
[0085] Through the above method, "abnormal" data is selected as training data for the model, so that the model is more targeted during training.
[0086] In addition, in order to ensure the training effect of the model, it is also necessary to obtain the group identification results corresponding to the abnormal order information when training the model as the annotation results during training. In an optional implementation, the group identification results can be obtained by verifying the abnormal order information set, such as the group identification result corresponding to [P1, D1, N1] is "illegal unlocking"; the group identification result corresponding to [P3, D2, N3] is "legal unlocking".
[0087] The verification process includes, but is not limited to, using manual offline verification to determine whether there is illegal unlocking behavior in the account or device involved in each order in the abnormal order information. The manual offline verification method may include reporting by others, telephone follow-up, etc., and the embodiments of the present disclosure do not impose any restrictions on this.
[0088] Finally, the processing device will also use the abnormal order information set and the corresponding group identification results to train the pre-built group identification model based on the graph algorithm. Specifically, the abnormal order information set includes the order volume of abnormal accounts on the device, or the order volume of abnormal devices on the account; during training, the order volume of abnormal accounts on the device in the abnormal order information set, or the order volume of abnormal devices on the account can be used as the model weight, and the group identification result can be used as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set, and obtains the trained group identification model.
[0089] Furthermore, account P and device D are points input to the model, the association relationship between account P and device D (such as P1-D1) is the edge, the order volume N is the weight of the edge, and the gang recognition model is used to iteratively train the points using graph algorithm clustering.
[0090] When the clustering result is the same as or highly similar to the group identification result, the trained group identification model is obtained. The trained group identification model can output identification results such as [P1, P2, P3, D1, D2, D3], which means that the group includes multiple group accounts and multiple group devices. There are many graph algorithms, such as the LOUVAIN algorithm, a community discovery algorithm in the graph algorithm, which takes the modularity of the community as the objective function and maximizes the modularity of the entire community network, that is, the entire community network presents a module clustering structure.
[0091] Among them, during training, the model parameters can be further adjusted according to the obtained model accuracy, precision, and recall rate to improve the accuracy and precision of the model and reduce the recall rate. For example, in the LOUVAIN algorithm, the size of the community can be changed by adjusting the resolution parameter.
[0092] The method for processing order information provided by the embodiments of the present disclosure can obtain an abnormal order information set and a corresponding group identification result by processing the buried data and the order data; then, the model is trained using the abnormal order information set and the corresponding group identification result to obtain a trained group identification model, and the trained group identification model can be used to process the order information set to be identified to obtain a group identification result; wherein, the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and the identification accuracy is high, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders.
[0093] Embodiment 2
[0094] Based on Example 1, Figure 4 It is a flowchart of another method for processing order information provided by this application, such as Figure 4 As shown, the method includes:
[0095] Step 201: Acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity of each account to be identified placed on each device to be identified;
[0096] Step 202: Use the trained group identification model to process the order information set to be identified to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group.
[0097] It should be noted that the order information processing method provided by the present disclosure can be specifically applied to an order information processing device, and the processing device can be specifically set Figure 2 The processing server 12 is shown.
[0098] The trained group identification model in the embodiment of the present disclosure is obtained by processing according to any of the above-mentioned order information processing methods. The embodiment of the present disclosure describes the process of using the trained group identification model.
[0099] First, the processing device needs to obtain an order information set to be identified, and the order information set should include the order quantity placed by each account to be identified on each device to be identified within a preset time period.
[0100] Specifically, in the process of obtaining the order information set to be identified, the processing device may first obtain the order data to be identified in the business service end, and then pre-process the order data to obtain the order quantities of different accounts to be identified under different devices to be identified, such as [account to be identified P', device to be identified D', order quantity N], wherein the method for obtaining the order quantity of each account to be identified under each device to be identified can be referred to the aforementioned implementation method, which will not be repeated in this embodiment.
[0101] Subsequently, the order information set to be identified is input into the trained group identification model, and a group identification result is output, such as the identification result of [P1', P2', P3', D1', D2', D3'], which includes at least one account to be identified belonging to the same group, and / or at least one device to be identified.
[0102] Through this implementation, orders in the business service end can be identified to identify abnormal orders that may be from group accounts or group devices, thereby facilitating subsequent processing.
[0103] In an optional implementation, in order to facilitate effective monitoring of business operations based on the identified results, the processing device will also establish an abnormal account device list based on the group identification results; the abnormal account device list includes all accounts and all devices belonging to the same group. Among them, for the processing device, its identification of orders should be periodic, that is, at intervals of a certain period of time, it is necessary to identify the order information set to be identified within the time period to obtain relevant information of the team account or team device, and each result obtained can be stored in the abnormal account device list for actual use.
[0104] Furthermore, the processing device may also be used to receive an order request, the order request including a target account and a target device for initiating the request, determine whether the target account and the target device belong to the abnormal account device list, and if so, refuse to respond to the order request.
[0105] Specifically, after receiving the unlocking request, the business service end may also forward the unlocking request to the processing device, so that the processing device can identify and determine the order based on the abnormal account device list therein. During the identification and determination process, once the target account or target device in the order request belongs to the abnormal account device list, the target account or target device may be a group account or group device. At this time, the processing device can generate a rejection response message to send to the business service end, so that the business service end can reject the response to the unlocking request based on the message, thereby ensuring that the illegal unlocking request of the abnormal user will not be responded to, and ensuring the normal operation of the business.
[0106] The method for processing order information provided by the embodiments of the present disclosure can be used to process the order information set to be identified by utilizing the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and having a high identification accuracy rate, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders.
[0107] Embodiment 3
[0108] Corresponding to the method for processing order information in the above embodiment, Figure 5 A structural block diagram of an order information processing device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 5 The order information processing device includes: a first acquisition module 100, a first processing module 200 and a training module 300.
[0109] The first acquisition module 100 is used to obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user;
[0110] The first processing module 200 is used to pre-process the historical order information set according to the tracking point data and the order data to obtain the abnormal order information set and the group identification result of the abnormal order information set;
[0111] The training module 300 is used to train a pre-built graph algorithm-based group identification model using the abnormal order information set and the corresponding group identification results to obtain a trained group identification model.
[0112] Optionally, the first processing module 200 is specifically used for:
[0113] According to the buried data, the order data of each user in the historical order information set is screened to obtain multiple candidate order data; based on the multiple candidate order data, an order information set is constructed, and the order information set is used to represent the correspondence between different accounts and different devices in each candidate order data; according to the correspondence between the accounts and devices in the order information set, the order data of accounts or devices with multilateral correspondence are selected from the order information set to generate the abnormal order information set.
[0114] Optionally, the buried data is operation data of the user performing operations at multiple key operation nodes;
[0115] The first processing module 200 is specifically used to: determine the key operation node coverage rate corresponding to the buried point data based on the operation data of the user operating on different key operation nodes in each buried point data; select the buried point data whose key operation node coverage rate is less than the first threshold, and use the order data of the user corresponding to the selected buried point data as the candidate order data.
[0116] Optionally, the first processing module 200 is specifically used to: determine the order volume generated by the same account under the same device among the multiple candidate order data; and generate the order information set according to the order volume generated by the same account under the same device.
[0117] Optionally, the first processing module 200 is specifically used to: select abnormal accounts or abnormal devices with multilateral correspondences from the order information set; wherein the abnormal accounts with opposite-side correspondences refer to accounts where the same account generates order volumes under multiple devices; the abnormal devices with multilateral correspondences refer to devices where multiple accounts generate order volumes under the same device; and generate the abnormal order information set using the abnormal accounts, their corresponding devices and order volumes, and the abnormal devices, their corresponding accounts and order volumes.
[0118] Optionally, the first processing module 200 is specifically used to verify the abnormal order information set to obtain the gang identification result.
[0119] Optionally, the abnormal order information set includes the order volume of the abnormal account placed on the device, or the order volume of the abnormal device placed on the account;
[0120] The training module 300 is used to: use the order volume of the abnormal account under the device in the abnormal order information set, or the order volume of the abnormal device under the account as the model weight, and use the group identification result as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set to obtain a trained group identification model.
[0121] Optionally, before obtaining the historical order information set, the first acquisition module 100 is further used to: perform data cleaning and extraction of preset fields on the obtained original historical order data to obtain the historical order information set.
[0122] The order information processing device provided by the embodiments of the present disclosure can obtain an abnormal order information set and a corresponding group identification result by processing the buried data and the order data; then, the model is trained using the abnormal order information set and the corresponding group identification result to obtain a trained group identification model, and the trained group identification model can be used to process the order information set to be identified to obtain a group identification result; wherein, the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and the identification accuracy is high, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders.
[0123] Embodiment 4
[0124] Figure 6 A structural block diagram of another order information processing device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 6 The order processing device includes: a second acquisition module 400 and a second processing module 500.
[0125] The second acquisition module 400 is used to acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity of each account to be identified placed on each device to be identified;
[0126] The second processing module 400 is used to process the order information set to be identified by using the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group;
[0127] The trained group identification model is obtained by processing the order information according to any of the above-mentioned methods.
[0128] Optionally, the processing device further includes: an abnormality monitoring module;
[0129] The abnormal monitoring module is used to establish an abnormal account device list according to the group identification result; the abnormal account device list includes all accounts and all devices belonging to the same group.
[0130] Optionally, the second acquisition module 400 is further configured to receive an order request, wherein the order request includes a target account and a target device for initiating the request;
[0131] The abnormal monitoring module is also used to: determine whether the target account and the target device belong to the abnormal account device list; if so, refuse to respond to the order request.
[0132] The order information processing device provided by the embodiments of the present disclosure can be used to process the order information set to be identified by utilizing the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified belonging to the same group, and / or, at least one technical means of a device to be identified, thereby realizing the identification of orders from group accounts or group devices in the order, and having a high identification accuracy rate, effectively ensuring the normal operation of the business, and avoiding the bad experience brought to users by illegal business orders.
[0133] Embodiment 5
[0134] The electronic device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.
[0135] refer to Figure 7 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a media library. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0136] like Figure 7 As shown, the electronic device 900 may include an order processing device (e.g., a central processing unit, a graphics processing unit, etc.) 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 device 908 to a random access memory (RAM) 903. Various programs and data required for the operation of the electronic device 900 are also stored in the RAM 903. The song release date recognition device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.
[0137] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0138] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the song release date recognition device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
[0139] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0140] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0141] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.
[0142] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or media library. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0143] A computer program product provided in this embodiment includes computer instructions, and the computer instructions are executed by a processor to implement the order processing method as described in any of the preceding items. The implementation principle and technical effects are similar, and will not be described in detail in this embodiment.
[0144] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / 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.
[0145] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".
[0146] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0147] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0148] In addition, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored; when the computer program is executed, the method described above is implemented.
[0149] The present application also provides the following embodiments:
[0150] Embodiment 1: A method for processing order information, comprising:
[0151] Obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user;
[0152] Pre-process the historical order information set according to the tracking point data and order data to obtain the abnormal order information set and the group identification result of the abnormal order information set;
[0153] The abnormal order information set and the corresponding group identification results are used to train a pre-built group identification model based on a graph algorithm to obtain a trained group identification model.
[0154] Embodiment 2: According to the processing method described in Embodiment 1, the historical order information set is preprocessed according to the tracking point data and the order data to obtain the abnormal order information set, including:
[0155] According to the buried data, the order data of each user in the historical order information set is screened to obtain multiple candidate order data;
[0156] Constructing an order information set according to the plurality of candidate order data, wherein the order information set is used to represent the correspondence between different accounts and different devices in each candidate order data;
[0157] According to the correspondence between the accounts and devices in the order information set, order data of accounts or devices having a multilateral correspondence is selected from the order information set to generate the abnormal order information set.
[0158] Embodiment 3, according to the processing method of embodiment 2, the buried point data is the operation data of the user operating at multiple key operation nodes;
[0159] The order data of each user in the historical order information set is screened according to the buried data to obtain multiple candidate order data, including:
[0160] Determine the coverage rate of the key operation nodes corresponding to the buried data according to the operation data of the user on different key operation nodes in each buried data;
[0161] The buried data whose coverage rate of the key operation nodes is less than the first threshold is selected, and the order data of the user corresponding to the selected buried data is used as the candidate order data.
[0162] Embodiment 4: According to the processing method described in Embodiment 2, the step of constructing an order information set based on a plurality of candidate order data includes:
[0163] Determine, from the plurality of candidate order data, the order quantity generated by the same account under the same device;
[0164] The order information set is generated according to the order quantity generated by the same account under the same device.
[0165] Embodiment 5, according to the processing method of embodiment 2, the selecting, according to the correspondence between the account and the device in the order information set, order data of the account or device having a multilateral correspondence from the order information set to generate the abnormal order information set includes:
[0166] From the order information set, select abnormal accounts or abnormal devices with multilateral correspondence; wherein the abnormal accounts with opposite-side correspondence refer to accounts where the same account generates order volumes under multiple devices; the abnormal devices with multilateral correspondence refer to devices where multiple accounts generate order volumes under the same device;
[0167] The abnormal account, its corresponding device and order amount, and the abnormal device, its corresponding account and order amount are used to generate the abnormal order information set.
[0168] Embodiment 6: According to the processing method described in Embodiment 2, a group identification result of an abnormal order information set is obtained, including:
[0169] The abnormal order information set is verified and processed to obtain the gang identification result.
[0170] Embodiment 7, according to the processing method of embodiment 1, the abnormal order information set includes the order quantity of the abnormal account under the device, or the order quantity of the abnormal device under the account;
[0171] The method of using the abnormal order information set and the corresponding group identification results to train a pre-built group identification model based on a graph algorithm includes:
[0172] The order volume of the abnormal account under the device in the abnormal order information set, or the order volume of the abnormal device under the account, is used as the model weight, and the group identification result is used as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set to obtain a trained group identification model.
[0173] Embodiment 8: According to the processing method of any one of embodiments 1 to 7, before obtaining the historical order information set, the method further includes:
[0174] The obtained original historical order data is cleaned and preset fields are extracted to obtain the historical order information set.
[0175] Embodiment 9: A method for processing order information, comprising:
[0176] Acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity placed by each account to be identified on each device to be identified;
[0177] Using the trained group identification model to process the order information set to be identified, to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group;
[0178] The trained group identification model is obtained by processing the order information according to any one of claims 1-8.
[0179] Embodiment 10: The processing method according to embodiment 9 further comprises:
[0180] According to the group identification result, an abnormal account device list is established; the abnormal account device list includes all accounts and all devices belonging to the same group.
[0181] Embodiment 11: The processing method according to embodiment 10 further includes:
[0182] Receiving an order request, wherein the order request includes a target account and a target device for initiating the request;
[0183] Determining whether the target account and the target device belong to the abnormal account device list;
[0184] If so, refuse to respond to the order request.
[0185] Embodiment 12: A device for processing order information, comprising:
[0186] A first acquisition module is used to obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user;
[0187] The first processing module is used to pre-process the historical order information set according to the buried point data and the order data to obtain the abnormal order information set and the group identification result of the abnormal order information set;
[0188] The training module is used to train a pre-built graph algorithm-based group identification model using the abnormal order information set and the corresponding group identification results to obtain a trained group identification model.
[0189] Embodiment 13: According to the processing device of embodiment 12, the first processing module is specifically used for:
[0190] According to the buried data, the order data of each user in the historical order information set is screened to obtain multiple candidate order data; based on the multiple candidate order data, an order information set is constructed, and the order information set is used to represent the correspondence between different accounts and different devices in each candidate order data; according to the correspondence between the accounts and devices in the order information set, the order data of accounts or devices with multilateral correspondence are selected from the order information set to generate the abnormal order information set.
[0191] Embodiment 14: According to the processing device of embodiment 13, the buried point data is operation data of the user operating at multiple key operation nodes;
[0192] The first processing module is specifically used to: determine the key operation node coverage rate corresponding to the buried point data based on the operation data of the user operating on different key operation nodes in each buried point data; select the buried point data whose key operation node coverage rate is less than the first threshold, and use the order data of the user corresponding to the selected buried point data as the candidate order data.
[0193] Embodiment 15, according to the processing device described in Embodiment 13, the first processing module is specifically used to: determine the order volume generated by the same account under the same device among the multiple candidate order data; generate the order information set according to the order volume generated by the same account under the same device.
[0194] Embodiment 16, according to the processing device described in Embodiment 13, the first processing module is specifically used to: select abnormal accounts or abnormal devices with multilateral correspondence relationships from the order information set; wherein the abnormal accounts with opposite-side correspondence relationships refer to accounts where the same account generates order volumes under multiple devices; the abnormal devices with multilateral correspondence relationships refer to devices where multiple accounts generate order volumes under the same device; the abnormal order information set is generated using the abnormal accounts, their corresponding devices and order volumes, and the abnormal devices, their corresponding accounts and order volumes.
[0195] Embodiment 17: According to the processing device described in Embodiment 13, the first processing module is specifically used to verify the abnormal order information set to obtain the gang identification result.
[0196] Embodiment 18, according to the processing device of embodiment 12, the abnormal order information set includes the order quantity placed by the abnormal account on the device, or the order quantity placed by the abnormal device on the account;
[0197] The training module is used to: use the order volume of abnormal accounts under the device in the abnormal order information set, or the order volume of abnormal devices under the account as the model weight, and use the group identification result as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set to obtain a trained group identification model.
[0198] Embodiment 19: According to the processing device described in any one of Embodiments 12-18, before obtaining the historical order information set, the first acquisition module is also used to: perform data cleaning and extraction of preset fields on the obtained original historical order data to obtain the historical order information set.
[0199] Embodiment 20: A device for processing order information, comprising:
[0200] A second acquisition module is used to acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity of each account to be identified placed on each device to be identified;
[0201] A second processing module, configured to process the order information set to be identified using the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group;
[0202] The trained group identification model is obtained by processing the order information according to any one of claims 1-8.
[0203] Embodiment 1: The processing device according to embodiment 20 further includes: an abnormality monitoring module;
[0204] The abnormal monitoring module is used to establish an abnormal account device list according to the group identification result; the abnormal account device list includes all accounts and all devices belonging to the same group.
[0205] Embodiment 22: According to the processing device of embodiment 21, the second acquisition module is further used to receive an order request, and the order request includes a target account and a target device for initiating the request;
[0206] The abnormal monitoring module is also used to: determine whether the target account and the target device belong to the abnormal account device list; if so, refuse to respond to the order request.
[0207] Embodiment 23: A device for processing order information, comprising: a memory and a processor;
[0208] The memory is used to store program instructions;
[0209] The processor is used to call the program instructions in the memory to execute the method described in any one of Examples 1-11.
[0210] Embodiment 24: A computer-readable storage medium having a computer program stored thereon; when the computer program is executed, the method described in any one of embodiments 1-11 is implemented.
[0211] Embodiment 25: A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in any one of embodiments 1-11.
[0212] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The embodiments of the present disclosure are intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0213] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A method for processing order information, characterized in that: include: Obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user; The buried point data is the operation data of the user performing operations at multiple key operation nodes; Preprocessing the historical order information set according to the tracking data and the order data to obtain an abnormal order information set and a group identification result of the abnormal order information set, including: The order data of each user in the historical order information set is screened according to the buried data to obtain a plurality of candidate order data, including: According to the operation data of the user operating different key operation nodes in the buried point data, the key operation node coverage rate corresponding to the buried point data is determined; the key operation node coverage rate is the ratio of the number of the key operation nodes having the operation data to the total number of the key operation nodes; Select the buried data whose coverage rate of the key operation nodes is less than the first threshold, and use the order data of the user corresponding to the selected buried data as the candidate order data; construct an order information set based on the plurality of candidate order data, wherein the order information set is used to represent the correspondence between different accounts and different devices in each candidate order data; According to the correspondence between the account and the device in the order information set, order data of the account or device with a multilateral correspondence is selected from the order information set to generate the abnormal order information set, including: selecting abnormal accounts or abnormal devices with a multilateral correspondence from the order information set; the accounts with a multilateral correspondence include accounts where the same account generates order volumes under multiple devices, and the devices with a multilateral correspondence include devices where multiple accounts generate order volumes under the same device; using the abnormal accounts, their corresponding devices and order volumes, and the abnormal devices, their corresponding accounts and order volumes to generate the abnormal order information set; The abnormal order information set and the corresponding group identification results are used to train a pre-built group identification model based on a graph algorithm to obtain a trained group identification model, including: using the order volume of the abnormal account under the device in the abnormal order information set, or the order volume of the abnormal device under the account as the model weight, and using the group identification results as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set to obtain a trained group identification model.
2. The processing method according to claim 1, characterized in that: The step of constructing an order information set according to the plurality of candidate order data includes: Determine, from the plurality of candidate order data, the order quantity generated by the same account under the same device; The order information set is generated according to the order quantity generated by the same account under the same device.
3. The processing method according to claim 1, characterized in that: The gang identification results of the abnormal order information set are obtained, including: The abnormal order information set is verified to obtain the group identification result.
4. The processing method according to any one of claims 1 to 3, characterized in that: Before obtaining the historical order information set, the method further includes: The obtained original historical order data is cleaned and preset fields are extracted to obtain the historical order information set.
5. A method for processing order information, characterized in that: include: Acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity placed by each account to be identified on each device to be identified; Using the trained group identification model to process the order information set to be identified, to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group; The trained group identification model is obtained by processing the order information according to any one of claims 1 to 4.
6. The processing method according to claim 5, characterized in that: Also includes: According to the group identification result, an abnormal account device list is established; the abnormal account device list includes all accounts and all devices belonging to the same group.
7. The processing method according to claim 6, characterized in that: Also includes: Receiving an order request, wherein the order request includes a target account and a target device for initiating the request; Determining whether the target account and the target device belong to the abnormal account device list; If so, refuse to respond to the order request.
8. An order information processing device, characterized in that: include: A first acquisition module is used to obtain a historical order information set, wherein the historical order information set includes at least the tracking point data of each user and the order data of each user; The buried point data is the operation data of the user performing operations at multiple key operation nodes; The first processing module is used to pre-process the historical order information set according to the tracking point data and the order data to obtain an abnormal order information set and a group identification result of the abnormal order information set; the first processing module is also used to: The order data of each user in the historical order information set is screened according to the buried data to obtain a plurality of candidate order data, including: determining the key operation node coverage rate corresponding to the buried data according to the operation data of the user operating on different key operation nodes in the buried data; the key operation node coverage rate is the ratio of the number of the key operation nodes having the operation data to the total number of the key operation nodes; selecting the buried data whose key operation node coverage rate is less than a first threshold, and using the order data of the user corresponding to the selected buried data as the candidate order data; According to the plurality of candidate order data, an order information set is constructed, the order information set being used to indicate the correspondence between different accounts and different devices in each candidate order data; according to the correspondence between the accounts and devices in the order information set, order data of accounts or devices with multilateral correspondence are selected from the order information set to generate the abnormal order information set, including: selecting abnormal accounts or abnormal devices with multilateral correspondence from the order information set; the accounts with multilateral correspondence include accounts where the same account generates order volumes under multiple devices, and the devices with multilateral correspondence include devices where multiple accounts generate order volumes under the same device; the abnormal accounts, their corresponding devices and order volumes, and the abnormal devices, their corresponding accounts and order volumes are used to generate the abnormal order information set; A training module is used to use the abnormal order information set and the corresponding group identification results to train a pre-built graph algorithm-based group identification model to obtain a trained group identification model, including: using the order volume of the abnormal account in the abnormal order information set under the device, or the order volume of the abnormal device under the account as the model weight, and using the group identification result as the model target, so that the group identification model iteratively learns the association relationship between each account and each device in the abnormal order information set to obtain a trained group identification model.
9. The processing device according to claim 8, characterized in that The first processing module is specifically used to: determine the order volume generated by the same account under the same device in the multiple candidate order data; and generate the order information set according to the order volume generated by the same account under the same device.
10. The processing device according to claim 8, characterized in that The first processing module is specifically used to verify the abnormal order information set to obtain the gang identification result.
11. The processing device according to any one of claims 8 to 10, characterized in that: Before obtaining the historical order information set, the first acquisition module is further used to: perform data cleaning and extraction of preset fields on the obtained original historical order data to obtain the historical order information set.
12. An order information processing device, characterized in that: include: A second acquisition module is used to acquire an order information set to be identified, wherein the order information set to be identified includes the order quantity of each account to be identified placed on each device to be identified; A second processing module, configured to process the order information set to be identified using the trained group identification model to obtain a group identification result; wherein the group identification result includes at least one account to be identified and / or at least one device to be identified belonging to the same group; The trained group identification model is obtained by processing the order information according to any one of claims 1 to 4.
13. The processing device according to claim 12, characterized in that Also includes: Abnormal monitoring module; The abnormal monitoring module is used to establish an abnormal account device list according to the group identification result; the abnormal account device list includes all accounts and all devices belonging to the same group.
14. The processing device according to claim 13, characterized in that The second acquisition module is further used to receive an order request, wherein the order request includes a target account and a target device for initiating the request; The abnormal monitoring module is also used to: determine whether the target account and the target device belong to the abnormal account device list; if so, refuse to respond to the order request.
15. An order information processing device, characterized in that: include: Memory and processor; The memory is used to store program instructions; The processor is used to call the program instructions in the memory to execute the method according to any one of claims 1-7.
16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program; when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.
17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.
