Behavior identification method, verification request sending method and device

Abstract

The present invention discloses a behavior recognition method, a method and device for sending a verification request, and relates to the field of computer technology. A specific implementation of the method includes: receiving a verification request for a target behavior sent by a client, the verification request including: task completion verification information and an operation behavior sequence; performing task completion verification on the verification request according to the task completion verification information; obtaining the client information corresponding to the client in response to the verification request passing the task completion verification, and determining the task completion forgery index corresponding to the verification request according to the task completion verification information and the client information; determining the human-computer recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence. This implementation can accurately determine the human-computer recognition result of the target behavior without affecting the user's normal operation of the system.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a behavior recognition method, a verification request sending device. Background Art

[0002] In marketing, gaming, voting and other activity scenarios, there are situations where machines simulate real people to operate through interface plug-ins, barrier-free touch plug-ins and other machines. This situation seriously affects the interests of other users. The server can determine the human-machine recognition results of the target behavior through verification code recognition, sliding track verification and other methods. However, the above methods will bring inconvenience to the user's normal operation of the system and affect the user's experience. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a behavior recognition method and device, which can accurately determine the human-machine recognition result of the target behavior without affecting the user's normal operation of the system.

[0004] In a first aspect, an embodiment of the present invention provides a behavior recognition method, including:

[0005] Receiving a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence;

[0006] Performing task completion verification on the verification request according to the task completion verification information;

[0007] In response to the verification request passing the task completion verification, obtaining client information corresponding to the client, and determining a task completion forgery index corresponding to the verification request based on the task completion verification information and the client information;

[0008] The human-machine recognition result of the target behavior is determined according to the task completion forgery index and the operation behavior sequence.

[0009] Optionally, the task completion verification information includes: the number of iterations;

[0010] The performing task completion verification on the verification request according to the task completion verification information includes:

[0011] Obtaining the initial value, task completion algorithm and algorithm rules corresponding to the verification request;

[0012] Determine an operation string according to the operation behavior sequence and the initial value;

[0013] Determine a calculation result corresponding to the calculation string, wherein the calculation result is a result of iterating the calculation string the number of times using the task completion algorithm;

[0014] Determining whether the operation result complies with the algorithm rule;

[0015] When the operation result complies with the algorithm rule, it is determined that the verification request passes the task completion verification.

[0016] Optionally, the task completion verification information includes: algorithm difficulty value, algorithm operation time; the client information includes: device processor model, device processor core number and device memory capacity;

[0017] The step of determining the task completion forgery index corresponding to the verification request according to the task completion verification information and the client information includes:

[0018] The algorithm difficulty value, the algorithm operation time, the device processor model, the number of device processor cores and the device memory capacity are input into the task completion verification model to obtain the task completion forgery index.

[0019] Optionally, determining the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence includes:

[0020] Parsing the operation behavior sequence to obtain operation behavior information corresponding to the operation behavior sequence;

[0021] The task completion forgery index and the operation behavior information are input into the behavior recognition model to obtain the human-machine recognition result.

[0022] Optionally, before receiving the verification request for the target behavior sent by the client, the method further includes:

[0023] Receiving a verification algorithm request sent by the client;

[0024] Determine the task completion algorithm information corresponding to the verification algorithm request, the task completion algorithm information including: initial value, task completion algorithm and algorithm rules;

[0025] The task completion algorithm information is sent to the client.

[0026] In a second aspect, an embodiment of the present invention provides a method for sending a verification request, including:

[0027] Collecting operation behavior information corresponding to the target behavior, and generating an operation behavior sequence according to the operation behavior information;

[0028] Acquire task completion algorithm information, and generate task completion verification information according to the task completion algorithm information and the operation behavior sequence;

[0029] Generating a verification request for the target behavior according to the task completion verification information and the operation behavior sequence;

[0030] The verification request is sent to a server.

[0031] Optionally, generating an operation behavior sequence according to the operation behavior information includes:

[0032] Obtaining client information corresponding to the client;

[0033] An operation behavior sequence is generated according to the operation behavior information and the client information.

[0034] Optionally, the task completion algorithm information includes: initial value, task completion algorithm and algorithm rules;

[0035] The step of generating task completion verification information according to the task completion algorithm information and the operation behavior sequence includes:

[0036] Determine an operation string according to the operation behavior sequence and the initial value;

[0037] According to the task completion algorithm and the algorithm rules, determining the number of iterations corresponding to the operation string so that the operation result corresponding to the operation string conforms to the algorithm rules, and the operation result is obtained after the operation string is operated for the number of iterations of the task completion algorithm;

[0038] The task completion verification information is generated according to the number of iterations.

[0039] Optionally, after determining the number of iterations corresponding to the operation string according to the task completion algorithm and the algorithm rule, the method further includes:

[0040] Determining the algorithm operation time required to obtain the number of iterations;

[0041] Generating the task completion verification information according to the number of iterations includes:

[0042] The task completion verification information is generated according to the number of iterations and the algorithm operation time.

[0043] Optionally, before obtaining the task completion algorithm information, the method further includes:

[0044] Send verification algorithm request;

[0045] Receive task completion algorithm information returned in response to the verification algorithm request, the task completion algorithm information including: an initial value, a task completion algorithm and an algorithm rule.

[0046] In a third aspect, an embodiment of the present invention provides a behavior recognition device, including:

[0047] A request receiving module, used to receive a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence;

[0048] A task completion verification module, used to perform task completion verification on the verification request according to the task completion verification information;

[0049] An index determination module, configured to obtain client information corresponding to the client in response to the verification request through task completion verification, and determine a task completion forgery index corresponding to the verification request based on the task completion verification information and the client information;

[0050] The result determination module is used to determine the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence.

[0051] In a fourth aspect, an embodiment of the present invention provides a device for sending a verification request, including:

[0052] A behavior collection module is used to collect operation behavior information corresponding to the target behavior and generate an operation behavior sequence according to the operation behavior information;

[0053] An information generation module, used to obtain task completion algorithm information, and generate task completion verification information according to the task completion algorithm information and the operation behavior sequence;

[0054] A request generation module, used to generate a verification request for the target behavior according to the task completion verification information and the operation behavior sequence;

[0055] The sending module is used to send the verification request to the server.

[0056] In a fifth aspect, an embodiment of the present invention provides an electronic device, including:

[0057] one or more processors;

[0058] a storage device for storing one or more programs,

[0059] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0060] In a sixth aspect, an embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the above embodiments.

[0061] One embodiment of the above invention has the following advantages or beneficial effects: according to the task completion verification information in the verification request for the target behavior sent by the client, the task completion verification is performed on the verification request. In the case where the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined. Finally, according to the task completion forgery index and the operation behavior sequence in the verification request, the human-machine recognition result of the target behavior is determined. Therefore, the human-machine recognition result of the target behavior can be accurately determined without affecting the user's normal operation of the system.

[0062] In addition, the solution of the embodiment of the present invention introduces a task completion proof mechanism, which can improve the resource consumption cost of machines such as hacker plug-ins to simulate real users to perform target behaviors, and reduce the risk of the system encountering batch requests from hacker plug-ins.

[0063] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0065] Figure 1 is a schematic diagram of a process of a behavior recognition method provided by an embodiment of the present invention;

[0066] Figure 2 It is a flow chart of a server verifying task completion provided by an embodiment of the present invention;

[0067] Figure 3 It is a schematic diagram of a process of a behavior recognition method integrating task completion proof provided by an embodiment of the present invention;

[0068] Figure 4 It is a schematic diagram of a process of a method for sending a verification request provided by an embodiment of the present invention;

[0069] Figure 5 It is a flowchart of a method for non-contact human-machine identification integrating task completion proof provided by an embodiment of the present invention;

[0070] Figure 6 is a structural schematic diagram of a behavior recognition device provided by an embodiment of the present invention;

[0071] Figure 7 It is a structural diagram of a device for sending a verification request provided by an embodiment of the present invention;

[0072] Figure 8 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0074] Figure 1 FIG. 1 is a schematic diagram of a process of a behavior recognition method provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0075] Step 101: receiving a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence.

[0076] The method of the embodiment of the present invention can be applied to the server side. The target behavior can be set according to the specific application scenario. In the game scenario, the target behavior can be the game operation behavior. In the voting scenario, the target behavior can be the voting operation behavior. In the online test scenario, the target behavior can be the answer input behavior, etc.

[0077] The method of the embodiment of the present invention adopts a task completion proof mechanism. The client needs to perform some time-consuming and complex calculations according to the task completion algorithm and algorithm rules to generate task completion verification information. The task completion verification information may include: initial value, task completion algorithm, algorithm rules, number of iterations, algorithm difficulty value, algorithm operation time, check digit, etc.

[0078] The server can quickly verify whether the client has performed the corresponding operation based on the verification request, thereby increasing the time and resource cost required for black market batch requests and ensuring that the target behavior is performed by real users.

[0079] The operation behavior sequence is generated based on the operation information for the target behavior. The operation behavior sequence can be set according to the needs. The form of the operation behavior sequence can be: coordinates ~ force ~ radius ~ force value, touch event ~ coordinates ~ force ~ radius ~ device hardware information, touch event * coordinates * force * radius * device hardware information * device software information, etc.

[0080] Step 102: Perform task completion verification on the verification request according to the task completion verification information.

[0081] Step 103: In response to the verification request, the task completion verification is performed, the client information corresponding to the client is obtained, and the task completion forgery index corresponding to the verification request is determined based on the task completion verification information and the client information.

[0082] When the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined. The task completion forgery index is used to characterize the possibility of forgery of the task completion verification information. The larger the task completion forgery index, the greater the possibility of forgery of the task completion verification information.

[0083] When the verification request fails the task completion verification, it is determined that the executor corresponding to the verification request is a machine.

[0084] Step 104: Determine the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence.

[0085] The human-machine identification result is used to characterize whether the target behavior is performed by a machine or a user. The human-machine identification result can correspond to two identification results: the target behavior is performed by a machine, and the target behavior is performed by a user.

[0086] In an embodiment of the present invention, task completion verification is performed on the verification request according to the task completion verification information in the verification request for the target behavior sent by the client. In the case where the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined. Finally, the human-machine recognition result of the target behavior is determined according to the task completion forgery index and the operation behavior sequence in the verification request. Therefore, the human-machine recognition result of the target behavior can be accurately determined without affecting the user's normal operation of the system.

[0087] In addition, the solution of the embodiment of the present invention introduces a task completion certification mechanism, which can improve the resource consumption cost of black market batch requests and reduce the risk of the system encountering black market batch requests.

[0088] In one embodiment of the present invention, before receiving a verification request for a target behavior sent by a client, it also includes: receiving a verification algorithm request sent by the client; determining task completion algorithm information corresponding to the verification algorithm request, the task completion algorithm information including: an initial value, a task completion algorithm and algorithm rules; and sending the task completion algorithm information to the client.

[0089] The server receives the verification algorithm request sent by the client, and sends random task completion algorithm information to the client through the pre-configured algorithm difficulty. The task completion algorithm information may include: initial value, algorithm rules, task completion algorithm, check digit, etc.

[0090] The initial value can be a random value. The algorithmic rules of the task completion algorithm are the target requirements that the calculation results should meet. The algorithmic rules can be set according to the needs, such as the first N bits of the calculation result are 0, the last N bits are 0, and the middle N bits are 1. The larger N is, the greater the algorithm difficulty value, the more iterations, and the more computing time it consumes.

[0091] The task completion algorithm is the algorithm used by the client to perform task calculations. The task completion algorithm can adopt the consensus algorithm of miners in the blockchain, commonly used hash algorithms, such as md5, sha1, sha256, sha512, etc. The client must perform calculations for the number of iterations before it can obtain calculation results that meet the algorithm rules. The number of iterations is usually large, which consumes a lot of time and resource costs. The server can verify whether the calculation results meet the algorithm rules through simple calculations based on the number of iterations.

[0092] The server uses the check digit to compare whether the check digit calculated by the server this time is consistent with the check digit included in the verification request. The calculation logic of the check digit can be set as needed. For example, the check digit can be obtained by the following formula: hmac256 (initial value + algorithm rule + task completion algorithm + device identifier, server key).

[0093] In one embodiment of the present invention, the verification algorithm request also includes: a client identifier of the client; after determining the task completion algorithm information corresponding to the verification algorithm request, it also includes: the server saves the correspondence between the client information and the task completion algorithm information. The client information may include: a client identifier, a device processor model, a device processor core number, and a device memory capacity. The task completion algorithm information may include: an initial value, an algorithm rule, a task completion algorithm, a check digit, an algorithm difficulty value, etc. On the one hand, the amount of data contained in the subsequent verification request returned by the client to the server can be reduced. On the other hand, the risk of the task completion algorithm information being tampered with by the client is reduced.

[0094] In one embodiment of the present invention, task completion verification information includes: the number of iterations; based on the task completion verification information, performing task completion verification on the verification request, including: obtaining the initial value, task completion algorithm and algorithm rules corresponding to the verification request; determining an operation string based on the operation behavior sequence and the initial value; determining the operation result of the operation string after the operation number of iterations of the task completion algorithm; determining whether the operation result complies with the algorithm rules; and if the operation result complies with the algorithm rules, determining that the verification request passes the task completion verification.

[0095] The server performs verification by extracting the verification request provided by the client. Figure 2 FIG. 1 is a flow chart of a server verifying task completion provided by an embodiment of the present invention. Figure 2 As shown, the server will first extract the check code in the verification request for verification. Specifically, the server calculates the check digit this time. The server compares the check digit this time with the check digit included in the verification request to verify the check code.

[0096] When the check digit meets the check condition, the task completion verification information and operation behavior sequence will be extracted to perform task completion verification calculation. According to the operation behavior sequence and the initial value, the operation string is determined. The operation behavior sequence and the initial value can be directly concatenated to obtain the operation string. It is also possible to extract a part of the string from the operation behavior sequence and concatenate it with the initial value to obtain the operation string.

[0097] After obtaining the number of iterations, the server can verify that the calculation result conforms to the algorithm rules and complete the task completion verification through simple calculations. The target behavior corresponding to the verification request that fails the task completion verification will be directly intercepted.

[0098] In one embodiment of the present invention, the task completion verification information includes: algorithm difficulty value, algorithm operation time; the client information includes: device processor model, device processor core number and device memory capacity; based on the task completion verification information and the client information, the task completion forgery index corresponding to the verification request is determined, including: inputting the algorithm difficulty value, algorithm operation time, device processor model, device processor core number and device memory capacity into the task completion verification model to obtain the task completion forgery index.

[0099] According to the task completion forgery index and the operation behavior sequence, the human-machine recognition result of the target behavior is determined, including: parsing the operation behavior sequence to obtain the operation behavior information corresponding to the operation behavior sequence; inputting the task completion forgery index and the operation behavior information into the behavior recognition model to obtain the human-machine recognition result.

[0100] The task completion forgery index is used to characterize the possibility of forgery of task completion verification information. The task completion verification model can select commonly used models, such as: support vector machine model, neural network model, etc. The behavior recognition model can select commonly used classification models, such as: decision tree model, support vector machine model, neural network model, GBDT (gradient boosting tree) model, etc.

[0101] Figure 3 FIG. 1 is a schematic diagram of a process of a behavior recognition method integrating task completion proof provided by an embodiment of the present invention. Figure 3 As shown, the data set is the data information obtained by parsing the task completion verification information and the operation behavior sequence. The data set can be divided into data set A and data set B. First, the client data related to task completion will be preprocessed and input into the SVM (support vector machine) model as data set A. Data set A corresponds to the task completion verification information and client information, and can include the following dimensional information: algorithm difficulty value, operation time, device processor model, device processor core number, device memory capacity, etc.

[0102] By inputting the dimension information in dataset A into the SVM model, the model outputs the task completion forgery index. Then the task completion forgery index and dataset B are used as an input of the GBDT model to obtain the final human-machine recognition result.

[0103] The dimensional information used in the GBDT model may include the following: task completion forgery index, click input device, click time, number of move events during the click process, maximum radius during the click process, minimum radius during the click process, click pressure, offset of the x-coordinate after the click, offset of the y-coordinate after the click, etc.

[0104] Figure 4 FIG. 1 is a schematic diagram of a process of sending a verification request provided by an embodiment of the present invention. Figure 4 As shown, the method includes:

[0105] Step 401: collect operation behavior information corresponding to the target behavior, and generate an operation behavior sequence according to the operation behavior information.

[0106] Table 1 Client collection information table

[0107] Fields Interpretation Touch Information Touch events, touch force, touch radius, pen strokes, etc. Honeypot information Malicious container detection, such as multiple openings, simulators, and other environments Device hardware information Brand, model version, processor model, etc. Device software information System version, serial number, etc.

[0108] As shown in Table 1, environmental information, operation behavior information and client information are collected in the client. Client information may include: device hardware and software information, etc. Generate an operation behavior sequence based on environmental information, operation behavior information and client information. Operation behavior information may include: touch information, click information, input information, etc. Touch information may include operation information such as pressing, lifting, and moving. The operation behavior sequence can be in the form of: coordinates~force~radius~force value, touch event~coordinates~force~radius~device hardware information, honeypot information*touch event*coordinates*force*radius*device hardware information*device software information, etc.

[0109] Step 402: Obtain task completion algorithm information, and generate task completion verification information based on the task completion algorithm information and the operation behavior sequence.

[0110] The task completion algorithm information may include: initial value, task completion algorithm and algorithm rules. According to the operation behavior sequence and the initial value, determine the operation string; according to the task completion algorithm and the algorithm rules, determine the number of iterations corresponding to the operation string, so that the operation result corresponding to the operation string conforms to the algorithm rules, and the operation result is obtained after the operation string is operated for the number of iterations of the task completion algorithm; according to the number of iterations, generate the task completion verification information.

[0111] The operation behavior sequence and the initial value may be concatenated to determine the operation string. A part of the string may also be intercepted from the operation behavior sequence and concatenated with the initial value to determine the operation string.

[0112] Step S01: Set the number of iterations to 1, use the task completion algorithm to process the operation string, and obtain the operation result.

[0113] Step S02: Determine whether the operation result complies with the algorithm rules.

[0114] If it meets the algorithm rules, then execute step S03. If it does not meet the algorithm rules, then execute step S04.

[0115] Step S03: Return the number of iterations and the process ends.

[0116] Step S04: add 1 to the number of iterations, process the calculation result using the task completion algorithm, and obtain the calculation result.

[0117] Step S02 is executed again until the obtained calculation result conforms to the algorithm rule.

[0118] Through the above method, the number of iterations corresponding to the operation behavior sequence can be determined. The server can verify whether the client has completed the preset computing task volume through the number of iterations, task completion algorithm and algorithm rules.

[0119] It is also possible to determine the algorithm operation time for the client to determine the number of iterations, and then generate task completion verification information based on the number of iterations and the algorithm operation time. Using the algorithm operation time, the forgery index of the task completion verification information can be better determined.

[0120] In one embodiment of the present invention, before obtaining the task completion algorithm information, it also includes: sending a verification algorithm request; receiving the task completion algorithm information returned in response to the verification algorithm request, and the task completion algorithm information includes: initial value, task completion algorithm and algorithm rules.

[0121] The server receives the verification algorithm request sent by the client, and sends random task completion algorithm information to the client through the pre-configured algorithm difficulty. The task completion algorithm information may include: initial value, algorithm rules, task completion algorithm, check digit, etc.

[0122] Step 403: Generate a verification request for the target behavior based on the task completion verification information and the operation behavior sequence.

[0123] Step 404: Send the verification request to the server.

[0124] The server can determine the behavior recognition result of the target behavior according to the verification request. If the behavior recognition result indicates that the target behavior is performed by a machine, the target behavior is intercepted to reduce the adverse effects of the machine behavior on the system and other real users.

[0125] In addition, when the algorithm is difficult, the client needs to go through a large number of iterations to obtain a calculation result that conforms to the algorithm rules. Therefore, the method of the embodiment of the present invention can improve the resource cost of hacker plug-ins and other machines simulating real users to perform target behaviors, and reduce the risk of the system encountering batch requests from black industries.

[0126] Figure 5 FIG. 1 is a flow chart of a method for non-contact human-machine recognition that integrates task completion proof and integrated learning, provided by an embodiment of the present invention. Figure 5 As shown, the browser is located in the client, the task completion algorithm is sent and the verification module is located on the server, and the operation identification module is located on the server.

[0127] The client obtains the task completion algorithm information of this session from the server. When the user performs business operations on the browser, a request for local task volume verification will be initiated to the client APP. The client APP collects the user's operation behavior information when performing the target behavior operation on the browser, and adds it to the prefix of the task volume verification request issued by the server to generate an operation string. Based on the task completion algorithm information, the corresponding task completion verification information is calculated and generated, returned to the embedded browser, and carried by the browser to the server. The server performs the corresponding task completion verification and human-machine recognition result verification based on the task completion verification information.

[0128] Figure 6 FIG. 1 is a schematic diagram of a behavior recognition device provided by an embodiment of the present invention. Figure 6 As shown, the device comprises:

[0129] The request receiving module 601 is used to receive a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence;

[0130] The task completion verification module 602 is used to perform task completion verification on the verification request according to the task completion verification information;

[0131] An index determination module 603 is used to obtain the client information corresponding to the client in response to the verification request passing the task completion verification, and determine the task completion forgery index corresponding to the verification request according to the task completion verification information and the client information;

[0132] The result determination module 604 is used to determine the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence.

[0133] Optionally, the task completion verification information includes: the number of iterations;

[0134] The task completion verification module 602 is specifically used for:

[0135] Obtaining the initial value, task completion algorithm and algorithm rules corresponding to the verification request;

[0136] Determine an operation string according to the operation behavior sequence and the initial value;

[0137] Determine the operation result of the operation string after the operation is performed the number of times of the task completion algorithm;

[0138] Determining whether the operation result complies with the algorithm rule;

[0139] When the operation result complies with the algorithm rule, it is determined that the verification request passes the task completion verification.

[0140] Optionally, the task completion verification information includes: algorithm difficulty value, algorithm operation time; the client information includes: device processor model, device processor core number and device memory capacity;

[0141] The index determination module 603 is specifically used for:

[0142] The algorithm difficulty value, the algorithm operation time, the device processor model, the number of device processor cores and the device memory capacity are input into the task completion verification model to obtain the task completion forgery index.

[0143] Optionally, the result determination module 604 is specifically configured to:

[0144] Parsing the operation behavior sequence to obtain operation behavior information corresponding to the operation behavior sequence;

[0145] The task completion forgery index and the operation behavior information are input into the behavior recognition model to obtain the human-machine recognition result.

[0146] Optionally, the device further comprises:

[0147] The information sending module 605 is used to receive the verification algorithm request sent by the client;

[0148] Determine the task completion algorithm information corresponding to the verification algorithm request, the task completion algorithm information including: initial value, task completion algorithm and algorithm rules;

[0149] The task completion algorithm information is sent to the client.

[0150] Figure 7 FIG. 1 is a schematic diagram of a structure of a device for sending a verification request provided by an embodiment of the present invention. Figure 7 As shown, the device comprises:

[0151] The behavior collection module 701 is used to collect the operation behavior information corresponding to the target behavior, and generate an operation behavior sequence according to the operation behavior information;

[0152] The information generation module 702 is used to obtain task completion algorithm information and generate task completion verification information according to the task completion algorithm information and the operation behavior sequence;

[0153] A request generation module 703, configured to generate a verification request for the target behavior according to the task completion verification information and the operation behavior sequence;

[0154] The sending module 704 is used to send the verification request to the server.

[0155] Optionally, the behavior collection module 701 is specifically used for:

[0156] Obtaining client information corresponding to the client;

[0157] An operation behavior sequence is generated according to the operation behavior information and the client information.

[0158] Optionally, the task completion algorithm information includes: initial value, task completion algorithm and algorithm rules;

[0159] The information generation module 702 is specifically used for:

[0160] Determine an operation string according to the operation behavior sequence and the initial value;

[0161] According to the task completion algorithm and the algorithm rules, determining the number of iterations corresponding to the operation string so that the operation result corresponding to the operation string conforms to the algorithm rules, and the operation result is obtained after the operation string is operated for the number of iterations of the task completion algorithm;

[0162] The task completion verification information is generated according to the number of iterations.

[0163] Optionally, the information generating module 702 is further used to:

[0164] Determine the algorithm operation time for the client to determine the number of iterations;

[0165] Generating the task completion verification information according to the number of iterations includes:

[0166] The task completion verification information is generated according to the number of iterations and the algorithm operation time.

[0167] Optionally, the device further comprises:

[0168] Receiving module 705, used to send a verification algorithm request;

[0169] Receive task completion algorithm information returned in response to the verification algorithm request, the task completion algorithm information including: an initial value, a task completion algorithm and an algorithm rule.

[0170] An embodiment of the present invention provides an electronic device, including:

[0171] one or more processors;

[0172] a storage device for storing one or more programs,

[0173] When one or more programs are executed by one or more processors, the one or more processors implement the method of any of the above embodiments.

[0174] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 800 of a terminal device suitable for implementing an embodiment of the present invention. Figure 8 The terminal 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 invention.

[0175] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0176] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0177] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a 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 part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-mentioned functions defined in the system of the present invention are executed.

[0178] It should be noted that the computer-readable medium shown in the present invention 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 invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, 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 appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0179] 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 invention. 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.

[0180] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be provided in a processor, for example, they may be described as: a request receiving module, a task completion verification module, an index determination module, and a result determination module. The names of these modules do not, in some cases, constitute limitations on the modules themselves, for example, the request receiving module may also be described as "a module for receiving a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence".

[0181] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0182] Receiving a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence;

[0183] Performing task completion verification on the verification request according to the task completion verification information;

[0184] In response to the verification request passing the task completion verification, obtaining client information corresponding to the client, and determining a task completion forgery index corresponding to the verification request based on the task completion verification information and the client information;

[0185] The human-machine recognition result of the target behavior is determined according to the task completion forgery index and the operation behavior sequence.

[0186] According to the technical solution of the embodiment of the present invention, the verification request is verified for task completion according to the task completion verification information in the verification request for the target behavior sent by the client. In the case where the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined. Finally, the human-machine recognition result of the target behavior is determined based on the task completion forgery index and the operation behavior sequence in the verification request. Therefore, the human-machine recognition result of the target behavior can be accurately determined without affecting the user's normal operation of the system.

[0187] In addition, the solution of the embodiment of the present invention introduces a task completion certification mechanism, which can improve the resource consumption cost of black market batch requests and reduce the risk of the system encountering black market batch requests.

[0188] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A behavior recognition method, characterized in that: include: Receiving a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence; Performing task completion verification on the verification request according to the task completion verification information; In response to the verification request passing the task completion verification, obtaining client information corresponding to the client, and determining a task completion forgery index corresponding to the verification request based on the task completion verification information and the client information; The human-machine recognition result of the target behavior is determined according to the task completion forgery index and the operation behavior sequence.

2. The method according to claim 1, characterized in that The task completion verification information includes: the number of iterations; The performing task completion verification on the verification request according to the task completion verification information includes: Obtaining the initial value, task completion algorithm and algorithm rules corresponding to the verification request; Determine an operation string according to the operation behavior sequence and the initial value; Determine a calculation result corresponding to the calculation string, wherein the calculation result is a result of iterating the calculation string the number of times using the task completion algorithm; Determining whether the operation result complies with the algorithm rule; When the operation result complies with the algorithm rule, it is determined that the verification request passes the task completion verification.

3. The method according to claim 1, characterized in that The task completion verification information includes: algorithm difficulty value, algorithm operation time; the client information includes: device processor model, device processor core number and device memory capacity; The step of determining the task completion forgery index corresponding to the verification request according to the task completion verification information and the client information includes: The algorithm difficulty value, the algorithm operation time, the device processor model, the number of device processor cores and the device memory capacity are input into the task completion verification model to obtain the task completion forgery index.

4. The method according to claim 1, characterized in that: The step of determining the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence includes: Parsing the operation behavior sequence to obtain operation behavior information corresponding to the operation behavior sequence; The task completion forgery index and the operation behavior information are input into the behavior recognition model to obtain the human-machine recognition result.

5. The method according to claim 1, characterized in that Before receiving the verification request for the target behavior sent by the client, the method further includes: Receiving a verification algorithm request sent by the client; Determine the task completion algorithm information corresponding to the verification algorithm request, the task completion algorithm information including: initial value, task completion algorithm and algorithm rules; The task completion algorithm information is sent to the client.

6. A method for sending a verification request, characterized in that: include: Collecting operation behavior information corresponding to the target behavior, and generating an operation behavior sequence according to the operation behavior information; Acquire task completion algorithm information, and generate task completion verification information according to the task completion algorithm information and the operation behavior sequence; Generating a verification request for the target behavior according to the task completion verification information and the operation behavior sequence; The verification request is sent to a server; wherein the server performs task completion verification on the verification request according to the task completion verification information in the verification request for the target behavior sent by the client; when the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined; and the human-machine recognition result of the target behavior is determined according to the task completion forgery index and the operation behavior sequence in the verification request.

7. The method according to claim 6, characterized in that The step of generating an operation behavior sequence according to the operation behavior information includes: Obtaining client information corresponding to the client; An operation behavior sequence is generated according to the operation behavior information and the client information.

8. The method according to claim 6, characterized in that The task completion algorithm information includes: initial value, task completion algorithm and algorithm rules; The step of generating task completion verification information according to the task completion algorithm information and the operation behavior sequence includes: Determine an operation string according to the operation behavior sequence and the initial value; According to the task completion algorithm and the algorithm rules, determining the number of iterations corresponding to the operation string so that the operation result corresponding to the operation string conforms to the algorithm rules, and the operation result is obtained after the operation string is operated for the number of iterations of the task completion algorithm; The task completion verification information is generated according to the number of iterations.

9. The method according to claim 8, characterized in that After determining the number of iterations corresponding to the operation string according to the task completion algorithm and the algorithm rules, the method further includes: Determining the algorithm operation time required to obtain the number of iterations; Generating the task completion verification information according to the number of iterations includes: The task completion verification information is generated according to the number of iterations and the algorithm operation time.

10. The method according to claim 6, characterized in that Before obtaining the task completion algorithm information, the method further includes: Send verification algorithm request; Receive task completion algorithm information returned in response to the verification algorithm request, the task completion algorithm information including: an initial value, a task completion algorithm and an algorithm rule.

11. A behavior recognition device, characterized in that: include: A request receiving module, used to receive a verification request for a target behavior sent by a client, wherein the verification request includes: task completion verification information and an operation behavior sequence; A task completion verification module, used to perform task completion verification on the verification request according to the task completion verification information; An index determination module, configured to obtain client information corresponding to the client in response to the verification request through task completion verification, and determine a task completion forgery index corresponding to the verification request based on the task completion verification information and the client information; The result determination module is used to determine the human-machine recognition result of the target behavior according to the task completion forgery index and the operation behavior sequence.

12. A device for sending a verification request, characterized in that: include: A behavior collection module is used to collect operation behavior information corresponding to the target behavior and generate an operation behavior sequence according to the operation behavior information; An information generation module, used to obtain task completion algorithm information, and generate task completion verification information according to the task completion algorithm information and the operation behavior sequence; A request generation module, used to generate a verification request for the target behavior according to the task completion verification information and the operation behavior sequence; A sending module is used to send the verification request to a server; wherein the server performs task completion verification on the verification request according to the task completion verification information in the verification request for the target behavior sent by the client; when the verification request passes the task completion verification, the task completion forgery index corresponding to the verification request is determined; and according to the task completion forgery index and the operation behavior sequence in the verification request, the human-machine recognition result of the target behavior is determined.

13. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-5 or 6-10.

14. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 or 6 to 10 is implemented.

Images