External service calling method and device, medium, electronic equipment and program product

Abstract

The invention relates to the technical field of external service calling, and provides an external service calling method and device, a medium, electronic equipment and a program product, and the method comprises the steps: obtaining a credibility score of a to-be-called external service, and enabling the credibility score to be in positive correlation with the reliability of the to-be-called external service; determining a sensitivity score of the to-be-transmitted data, wherein the sensitivity score is in positive correlation with the data sensitivity degree of the to-be-transmitted data; determining a risk threshold according to the situation of the to-be-transmitted data; determining a calling risk value according to the credibility score and the sensitivity score; and calling the external service to be called according to the calling risk value and the risk threshold value. When the calling risk value is within the acceptable range set by the risk threshold value, calling is executed, post-remedy is converted into beforehand prevention, high-sensitivity data is strictly prevented from flowing to low-credibility service, meanwhile, the capacity of an intelligent agent for efficiently utilizing external service within the security boundary is guaranteed, and the safety of the intelligent agent is improved. Therefore, key balance is achieved between safety and efficiency.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of external service calling, in particular, to an external service calling method, device, medium, electronic equipment and program product. BACKGROUND

[0002] With the rapid development of large models and multi-agent technologies, agents often need to call different external services when performing complex tasks, such as text generation, image recognition, speech analysis, and data calculation.

[0003] In related technologies, external services are generally called directly when needed, but if the external services are not secure, it may lead to information leakage and cause irreparable losses. SUMMARY

[0004] The purpose of the present disclosure is to provide an external service calling method, device, medium, electronic equipment and program product to solve the problems in related technologies.

[0005] To achieve the above purpose, the present disclosure provides an external service calling method, comprising: obtaining a trust score of an external service to be called, the trust score being positively correlated with the reliability of the external service to be called; determining a sensitivity score of data to be transmitted, the sensitivity score being positively correlated with the data sensitivity of the data to be transmitted; determining a risk threshold according to a situation in which the data to be transmitted is located; determining a calling risk value according to the trust score and the sensitivity score; calling the external service to be called according to the calling risk value and the risk threshold.

[0006] Optionally, the trust score is determined according to at least one of service source, authentication information, historical interaction behavior, and verifiable security endorsement.

[0007] Optionally, the sensitivity score is determined according to the intentionality of the data to be transmitted and the external service to be called, and content analysis of the data to be transmitted. Figure One

[0008] Optionally, the risk threshold is determined according to at least one of a user role involved in the data to be transmitted, a data classification corresponding to the data to be transmitted, a geographic location where the data to be transmitted is located, a calling time period corresponding to the data to be transmitted, and compliance requirements corresponding to the data to be transmitted.

[0009] Optionally, the calculation formula of the calling risk value is as follows: ​R=β / α wherein R represents the calling risk value, β represents the sensitivity score, and α represents the reliability score.

[0010] Optionally, the calling the external service according to the calling risk value and the risk threshold comprises: blocking the calling of the external service to be called when the calling risk value is greater than the risk threshold; allowing the calling of the external service to be called when the calling risk value is less than or equal to the risk threshold.

[0011] Optionally, the risk threshold comprises a first risk threshold and a second risk threshold, the first risk threshold being less than the second risk threshold, and the calling the external service according to the calling risk value and the risk threshold comprises: allowing the calling of the external service to be called when the calling risk value is less than or equal to the first risk threshold; sending a confirmation message to a user when the calling risk value is greater than the first risk threshold and less than the second risk threshold, and allowing the calling of the external service to be called after receiving a confirmation reply from the user; blocking the calling of the external service to be called when the calling risk value is greater than or equal to the second risk threshold.

[0012] Optionally, the allowing the calling of the external service to be called comprises: generating test data according to the data to be transmitted, and sending the test data to the external service to be called to determine whether the external service to be called is reliable, and sending the data to be transmitted to the external service to be called to implement the calling when it is determined that the external service to be called is reliable.

[0013] Optionally, the sending the data to be transmitted to the external service to be called to implement the calling comprises: desensitizing sensitive data in the data to be transmitted, and sending the desensitized data to the external service to be called to implement the calling.

[0014] Optionally, the external service calling method further comprises: receiving a calling result returned by the external service to be called, verifying the calling result, and feeding back the calling result to a user when the verification is passed.

[0015] The present disclosure also provides an external service calling device, comprising: a first processing module configured to obtain a trust score of the external service to be invoked, the trust score being positively correlated with reliability of the external service to be invoked; a second processing module configured to determine a sensitivity score of the data to be transmitted, the sensitivity score being positively correlated with data sensitivity of the data to be transmitted; a third processing module configured to determine a risk threshold according to a context in which the data to be transmitted is located; a fourth processing module configured to determine a calling risk value according to the trust score and the sensitivity score; a fifth processing module configured to call the external service to be invoked according to the calling risk value and the risk threshold.

[0016] The disclosure also provides a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps of the external service calling method.

[0017] The disclosure also provides an electronic device, comprising: a memory having a computer program stored thereon; a processor configured to execute the computer program in the memory to implement the steps of the external service calling method.

[0018] The disclosure also provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the steps of the external service calling method.

[0019] Through the above technical solution, the reliability of the external service is evaluated through the trust score of the external service to be invoked, the data sensitivity of the data to be transmitted is evaluated through the sensitivity score of the data to be transmitted, then the risk threshold representing the security standard is set flexibly according to the context in which the data to be transmitted is located, so that the security standard is flexibly adapted to the actual situation, and the calling risk value is determined according to the trust score and the sensitivity score; finally, the external service to be invoked is called according to the calling risk value and the risk threshold, the calling is performed only when the calling risk value is within the acceptable range set by the risk threshold, the after-the-fact remedy is changed to the pre-emptive prevention, the ability of the intelligent agent to efficiently utilize the external service within the security boundary is ensured while strictly preventing the flow of high-sensitive data to low-trust services, and thus a key balance between security and efficiency is achieved.

[0020] Other features and advantages of the disclosure will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating an external service invocation method according to an exemplary embodiment.

[0022] Figure 2 This is a block diagram illustrating an external service invocation device according to an exemplary embodiment.

[0023] Figure 3 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0024] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0025] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0026] With the rapid development of large model and multi-agent technologies, intelligent agents often need to call different external services when performing complex tasks, such as text generation, image recognition, speech analysis, and data computation.

[0027] In related technologies, external services are typically invoked directly when needed. However, if the external service is insecure, it may lead to information leakage and cause irreparable damage.

[0028] Specifically, the inventors discovered that directly calling external services has at least the following problems: First, the lack of trusted verification for service calls means that users cannot confirm whether the services called by the agent are compliant, which poses a risk of data leakage. Second, sensitive information is leaked out uncontrollably, and user input is often directly passed to the service without sensitivity analysis and minimization protection before the call; Third, there is the risk of hackers forging services. Attackers can induce intelligent agents to transmit private or corporate secrets by forging APIs / services. Fourth, post-invoke auditing cannot prevent this; currently, it relies heavily on log auditing after the call, and cannot effectively block it before the call.

[0029] To address the aforementioned issues, the reliability of the external service to be invoked is first assessed through a trustworthiness score, and the sensitivity of the data to be transmitted is assessed through a sensitivity score. Then, risk thresholds representing security standards are flexibly and realistically set based on the context of the data to be transmitted, ensuring that security standards are flexible and practical. Next, the invocation risk value is determined based on the trustworthiness and sensitivity scores. Finally, the external service to be invoked is invoked based on the invocation risk value and risk threshold. The invocation is only executed when the invocation risk value is within the acceptable range set by the risk threshold. This shifts from post-event remediation to pre-event prevention, strictly preventing highly sensitive data from flowing to low-trust services while also ensuring the agent's ability to efficiently utilize external services within security boundaries, thus achieving a crucial balance between security and efficiency.

[0030] Figure 1 This is a flowchart illustrating an external service invocation method according to an exemplary embodiment. This external service invocation method can be applied to electronic devices. Please refer to [link / reference]. Figure 1 The external service invocation method may include steps S1 to S5.

[0031] Step S1: Obtain the credibility score of the external service to be invoked.

[0032] The credibility score is positively correlated with the reliability of the external service to be invoked.

[0033] The higher the reliability of the external service to be invoked, the higher the trust score; the lower the reliability of the external service to be invoked, the lower the trust score.

[0034] External services can be, for example, AI services, database services, third-party API services, etc.

[0035] In one possible implementation, the trust score can be determined based on at least one of the following: service origin, authentication information, historical interaction behavior, and verifiable security endorsement.

[0036] The service source indicates the background of the service provider offering the external service. If the entity has a strong background, it indicates that the external device to be called is highly reliable, which will increase the credibility score. If it comes from an unknown individual developer, a registered shell company, or a newly established startup, it indicates that the external device to be called is unreliable, which will decrease the credibility score.

[0037] The certification information indicates whether the service provider has passed the security audit and standard certification of a third-party authoritative organization. If it has certifications such as ISO 27001 (Information Security Management), SOC2 (Service Provider Control System), Level 3 Information Security Protection, and PCI DSS (Payment Card Industry Security Standard), it indicates that the external device to be called has high reliability, which will increase the credibility score. If there is no publicly available certification information, or if its claimed certification cannot be verified, it indicates that the external device to be called has low reliability, which will decrease the credibility score.

[0038] Historical interaction behavior represents the history of past interactions with the external service. If the service has a high success rate and responds quickly in past calls, and has never returned abnormal or malicious data, the behavior record is good, indicating that the external device to be called has high reliability, which will increase the credibility score. If the service frequently times out, crashes, or has returned incorrect or suspicious results, it has a bad record, indicating that the external device to be called has low reliability, which will decrease the credibility score.

[0039] Verifiable security endorsement represents the security commitments and proofs provided by the service provider that can be verified in real time by technical means. If they can be verified remotely, digitally, or through supply chain verification, it indicates that the external device to be called has high reliability, which will increase the credibility score. If the service provider only provides verbal or written security commitments but cannot provide any technical verification methods, it indicates that the external device to be called has low reliability, which will decrease the credibility score.

[0040] In other embodiments, a weighted calculation can be performed based on all four dimensions to obtain a more accurate credibility score.

[0041] Step S2: Determine the sensitivity score of the data to be transmitted.

[0042] The data to be transmitted is the data that will be subsequently transmitted to external services for service calls.

[0043] The sensitivity score is positively correlated with the sensitivity of the data to be transmitted.

[0044] The greater the sensitivity of the data to be transmitted, the higher the sensitivity score; conversely, the less sensitive the data to be transmitted, the lower the sensitivity score.

[0045] In one possible implementation, sensitivity scoring is based on the relevance of the data to be transmitted to the external service to be invoked. Figure One Consistency and content analysis of the data to be transmitted are used to determine this.

[0046] Sensitivity scoring can be based on the relationship between the data to be transmitted and the external service to be invoked. Figure OneThe consistency score obtained from the consistency test and the weighted composite score obtained from the content score based on the content analysis of the data to be transmitted can be set with corresponding weight values ​​according to the actual situation.

[0047] The meaning of the data to be transmitted and the external service to be invoked Figure One Consistency can be understood as analyzing whether the semantics of the data to be transmitted match the semantics of the external service function to be invoked. If they match, the consistency score will decrease; if they do not match, the consistency score will increase.

[0048] Content analysis of transmitted data can be understood as identifying personal privacy, corporate secrets, or structured sensitive fields in the data to be transmitted. If these are identified, it indicates a high degree of data sensitivity, which will increase the content score; if they are not identified, it indicates a low degree of data sensitivity, which will decrease the content score.

[0049] Step S3: Determine the risk threshold based on the context of the data to be transmitted.

[0050] The context of the data to be transmitted can include, but is not limited to, the user roles involved in the data to be transmitted, the data classification corresponding to the data to be transmitted, the geographical location of the data to be transmitted, the time period for the data to be transmitted, and the compliance requirements corresponding to the data to be transmitted.

[0051] In one possible implementation, the risk threshold is determined based on at least one of the following: the user role involved in the data to be transmitted, the data classification corresponding to the data to be transmitted, the geographical location of the data to be transmitted, the time period for the call corresponding to the data to be transmitted, and the compliance requirements corresponding to the data to be transmitted.

[0052] The user roles involved in the data to be transmitted can represent the identity of the user who initiated the data transmission request and the permissions they have. If the permissions are low, a lower risk threshold can be set, and if the permissions are high, a higher risk threshold can be set.

[0053] The data classification corresponding to the data to be transmitted can represent the division of the data to be transmitted into multiple data confidentiality levels, such as first confidentiality level, second confidentiality level, third confidentiality level, and fourth confidentiality level. As the confidentiality level increases, the corresponding data to be transmitted is more confidential, and correspondingly, the risk threshold set is lower. That is, the risk threshold corresponding to the first confidentiality level is greater than the risk threshold corresponding to the second confidentiality level, the risk threshold corresponding to the second confidentiality level is greater than the risk threshold corresponding to the third confidentiality level, and the risk threshold corresponding to the third confidentiality level is greater than the risk threshold corresponding to the fourth confidentiality level.

[0054] The geographical location of the data to be transmitted can be set. If the geographical location of the data to be transmitted is safe, a higher risk threshold can be set. If the geographical location of the data to be transmitted is not safe, a lower risk threshold can be set.

[0055] The call period corresponding to the data to be transmitted can represent the specific time period for calling the external device. If the time period is during working hours, a higher risk threshold can be set; if the time period is during non-working hours, a lower risk threshold can be set.

[0056] The compliance requirements for the data to be transmitted can refer to industry rules or regional rules. If the data to be transmitted meets the corresponding rules, a lower risk threshold can be set; if the data to be transmitted does not meet the corresponding rules, a higher risk threshold can be set.

[0057] In high-risk scenarios, the strategy is automatically tightened, and the risk threshold is lowered to ensure safe operation. In low-risk scenarios, the strategy is appropriately relaxed, and the risk threshold is raised to ensure business efficiency.

[0058] Step S4: Determine the call risk value based on the credibility score and sensitivity score.

[0059] In one possible implementation, the risk value is calculated as follows: R=β / α Among them, R represents the call risk value, β represents the sensitivity score, and α represents the credibility score.

[0060] Step S5: Based on the call risk value and risk threshold, invoke the external service to be invoked.

[0061] In one possible implementation, step S5 may include: If the risk value exceeds the risk threshold, the call to the external service to be called will be blocked. Calls to external services are permitted if the risk value is less than or equal to the risk threshold.

[0062] In another possible implementation, the risk threshold includes a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold, and step S5 may include: Calling the external service to be called is permitted if the risk value is less than or equal to the first risk threshold. If the risk value is greater than the first risk threshold but less than the second risk threshold, a confirmation message is sent to the user, and the external service to be called is allowed after receiving the user's confirmation reply. If the risk value is greater than or equal to the second risk threshold, the call to the external service to be called will be blocked.

[0063] If the call risk value is less than or equal to the first risk threshold, it is considered low risk and the call is allowed. If the call risk value is greater than the first risk threshold but less than the second risk threshold, it is considered medium risk, and user confirmation is required before the call is allowed. If the call risk value is greater than or equal to the second risk threshold, it is considered high risk, and the call is blocked. Different colors can also be used to indicate different risk levels, such as green for low risk, yellow for medium risk, and red for high risk, to quickly inform the user of the current risk level of the call.

[0064] In one possible implementation, allowing the invocation of an external service to be invoked may include: Test data is generated based on the data to be transmitted, and the test data is sent to the external service to be called to determine whether the external service is reliable. If the external service is found to be reliable, the data to be transmitted is sent to the external service to be called to implement the call.

[0065] Test data can be simulated data generated based on the data to be transmitted, such as virtual probe data or decoy data.

[0066] Sending test data to the external service to be called to determine whether the external service is reliable can be understood as sending test data to the external service to be called and judging its reliability by analyzing the external service's response to the test data. The judgment criteria can be, but are not limited to, the external service's functions, performance, behavior, authenticity, etc.

[0067] In one embodiment, the reliability of the external service to be invoked can be determined by setting up a buffer for shadow execution or honeypot detection.

[0068] In one possible implementation, sending the data to be transmitted to the external service implementation to be invoked may include: Sensitive data in the data to be transmitted is anonymized, and the anonymized data is then sent to the external service to be invoked.

[0069] Desensitizing sensitive data in the transmitted data can involve transforming, replacing, or deleting the sensitive data while retaining its data format and some characteristics, but losing its direct identifiability.

[0070] By de-identifying the data, external services receive data that can still be used in their business logic, but even if leaked, it cannot be directly traced back to a specific individual or cause direct loss.

[0071] In another embodiment, sensitive data can be pruned or digested, and if necessary, the task can be broken down into multiple sub-tasks and distributed to different trusted services.

[0072] In one possible implementation, the external service invocation method may further include: Receive the call result returned by the external service to be invoked, verify the call result, and if the verification is successful, return the call result to the user.

[0073] Perform source verification and sensitivity testing on the service return results to prevent the original text from being leaked. Source verification can be, but is not limited to, signatures, watermarks, Trusted Execution Environment (TEE) certifications, etc.

[0074] In other embodiments, risk assessment, interception behavior, and detection results can be written into an anti-tampering ledger, and the credibility score and sensitivity score can be continuously updated through a human-machine co-training mechanism.

[0075] In one embodiment of enterprise financial data protection, a user requests an agent to "summarize the company's internal financial statements." The system detects that the input contains confidential fields (high sensitivity score), the external service being called has a low credibility score, and the call risk value is greater than the second risk threshold, triggering a high-risk red screen warning and blocking the call.

[0076] In one embodiment of cross-border call compliance control, a user calls an overseas text generation model, inputs employee information, the overseas service is of low trustworthiness and contains private data, the call risk value is greater than the second risk threshold, the call is intercepted and an audit log is generated.

[0077] In one embodiment of anti-forgery service attack, when an agent attempts to call an unknown API service, the system injects honeypot data, detects the data leakage, determines the service to be forged, and automatically blacklists and blocks the call.

[0078] In a minimized and secure routing implementation, users upload images of medical records for diagnosis. The system desensitizes the case number and patient name, transmitting only image features to reduce the risk of sensitive information leakage.

[0079] The external service invocation method provided by this invention has at least the following advantages: First, pre-call blocking, which completes detection and interception before data is sent, is superior to traditional post-event auditing.

[0080] Second, a multi-dimensional integrated judgment is adopted, combining sensitivity score, credibility score, and risk threshold to achieve more accurate risk assessment.

[0081] Third, a tiered blocking mechanism strikes a balance between security and availability, rather than a one-size-fits-all approach.

[0082] Fourth, proactively defend against hacker attacks by using honeypot detection and shadow execution to identify spoofed services.

[0083] Fifth, the minimization and fragmentation strategy reduces the risk of single point of leakage and ensures task completion.

[0084] Sixth, full-chain traceability, log ledger and parameter co-training mechanism ensure compliance and continuous optimization.

[0085] Based on the same inventive concept, this disclosure also provides an external service invocation device. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a block diagram illustrating an external service invocation apparatus 600 according to an exemplary embodiment, the external service invocation apparatus 600 may include: The first processing module 601 is configured to obtain the credibility score of the external service to be called, and the credibility score is positively correlated with the reliability of the external service to be called. The second processing module 602 is configured to determine the sensitivity score of the data to be transmitted, and the sensitivity score is positively correlated with the sensitivity of the data to be transmitted. The third processing module 603 is configured to determine a risk threshold based on the context of the data to be transmitted; The fourth processing module 604 is configured to determine the call risk value based on the credibility score and sensitivity score; The fifth processing module 605 is configured to invoke the external service to be invoked based on the invocation risk value and risk threshold.

[0086] Optionally, the credibility score is determined based on at least one of the following: service origin, authentication information, historical interaction behavior, and verifiable security endorsement.

[0087] Optionally, the sensitivity score is based on the relevance of the data to be transmitted to the external service to be invoked. Figure One Consistency and content analysis of the data to be transmitted are used to determine this.

[0088] Optionally, the risk threshold is determined based on at least one of the following: the user role involved in the data to be transmitted, the data classification corresponding to the data to be transmitted, the geographical location of the data to be transmitted, the time period for the data to be transmitted, and the compliance requirements corresponding to the data to be transmitted.

[0089] Optionally, the formula for calculating the risk value is as follows: R=β / α Among them, R represents the call risk value, β represents the sensitivity score, and α represents the credibility score.

[0090] Optionally, the fifth processing module 605 may include: The first sub-processing module is configured to block calls to external services if the risk value exceeds the risk threshold. The second sub-processing module is configured to allow the external service to be called if the risk value is less than or equal to the risk threshold.

[0091] Optionally, the risk threshold includes a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold, and the fifth processing module 605 may include: The third sub-processing module is configured to allow the external service to be called to be invoked if the risk value is less than or equal to the first risk threshold. The fourth sub-processing module is configured to send a confirmation message to the user when the call risk value is greater than the first risk threshold and less than the second risk threshold, and to allow the external service to be called to be called after receiving the user's confirmation reply; The fifth sub-processing module is configured to block the external service to be called if the risk value is greater than or equal to the second risk threshold.

[0092] Optionally, the second, third, and fourth sub-processing modules allow invocation of external services to be called, including: Test data is generated based on the data to be transmitted, and the test data is sent to the external service to be called to determine whether the external service is reliable. If the external service is found to be reliable, the data to be transmitted is sent to the external service to be called to implement the call.

[0093] Optionally, the second, third, and fourth sub-processing modules send the data to be transmitted to the external service to be invoked, including: Sensitive data in the data to be transmitted is anonymized, and the anonymized data is then sent to the external service to be invoked.

[0094] Optionally, the external service invocation device 600 may further include: The sixth processing module is configured to receive the call result returned by the external service to be called, verify the call result, and if the verification is successful, return the call result to the user.

[0095] Regarding the external service invocation device in the above embodiments, the specific methods by which each module performs operations have been described in detail in the embodiments related to the external service invocation method, and will not be elaborated here.

[0096] Figure 3 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment. Figure 3 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0097] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the external service call method described above. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof; therefore, the corresponding communication component 705 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0098] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the external service invocation method described above.

[0099] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the external service invocation method described above. For example, the computer-readable storage medium may be the memory 702 including the program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the external service invocation method described above.

[0100] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the external service invocation method described above.

[0101] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0102] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0103] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for invoking an external service, characterized in that, include: Obtain the credibility score of the external service to be invoked, wherein the credibility score is positively correlated with the reliability of the external service to be invoked; A sensitivity score is determined for the data to be transmitted, wherein the sensitivity score is positively correlated with the data sensitivity of the data to be transmitted; Determine the risk threshold based on the context of the data to be transmitted; The call risk value is determined based on the credibility score and the sensitivity score. The external service to be invoked is invoked based on the invocation risk value and the risk threshold.

2. The external service invocation method according to claim 1, characterized in that, The credibility score is determined based on at least one of the following: service origin, authentication information, historical interaction behavior, and verifiable security endorsement.

3. The external service invocation method according to claim 1, characterized in that, The sensitivity score is determined based on the consistency between the data to be transmitted and the intent of the external service to be invoked, as well as the content analysis of the data to be transmitted.

4. The external service invocation method according to claim 1, characterized in that, The risk threshold is determined based on at least one of the following: the user role involved in the data to be transmitted, the data classification corresponding to the data to be transmitted, the geographical location of the data to be transmitted, the call time period corresponding to the data to be transmitted, and the compliance requirements corresponding to the data to be transmitted.

5. The external service invocation method according to claim 1, characterized in that, The formula for calculating the risk value of the call is as follows: R=β / α Where R represents the call risk value, β represents the sensitivity score, and α represents the credibility score.

6. The external service invocation method according to claim 1, characterized in that, The step of invoking the external service to be invoked based on the invocation risk value and the risk threshold includes: If the risk value exceeds the risk threshold, the call to the external service to be invoked will be blocked. If the risk value is less than or equal to the risk threshold, the external service to be invoked is permitted.

7. The external service invocation method according to claim 1, characterized in that, The risk threshold includes a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. The step of invoking the external service to be invoked based on the invocation risk value and the risk threshold includes: If the risk value is less than or equal to the first risk threshold, the external service to be invoked is permitted. If the risk value of the call is greater than the first risk threshold and less than the second risk threshold, a confirmation message is sent to the user, and after receiving the user's confirmation reply, the call to the external service to be called is allowed; If the risk value of the call is greater than or equal to the second risk threshold, the call to the external service to be called will be blocked.

8. The external service invocation method according to claim 6 or 7, characterized in that, The permission to invoke the external service to be invoked includes: Test data is generated based on the data to be transmitted, and the test data is sent to the external service to be called to determine whether the external service to be called is reliable. If the external service to be called is determined to be reliable, the data to be transmitted is sent to the external service to be called to realize the call.

9. The external service invocation method according to claim 8, characterized in that, The step of sending the data to be transmitted to the external service to be invoked to implement the invocation includes: Sensitive data in the data to be transmitted is de-identified, and the de-identified data is sent to the external service to be invoked for invocation.

10. The external service invocation method according to claim 1, characterized in that, The external service invocation method also includes: The system receives the call result returned by the external service to be invoked, verifies the call result, and if the verification is successful, feeds back the call result to the user.

11. An external service invocation device, characterized in that, include: The first processing module is configured to obtain the credibility score of the external service to be invoked, wherein the credibility score is positively correlated with the reliability of the external service to be invoked; The second processing module is configured to determine a sensitivity score of the data to be transmitted, wherein the sensitivity score is positively correlated with the data sensitivity of the data to be transmitted; The third processing module is configured to determine a risk threshold based on the context of the data to be transmitted; The fourth processing module is configured to determine the call risk value based on the credibility score and the sensitivity score; The fifth processing module is configured to invoke the external service to be invoked based on the invocation risk value and the risk threshold.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the external service invocation method as described in any one of claims 1-10.

13. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the external service invocation method according to any one of claims 1-10.

14. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the external service invocation method as described in any one of claims 1-10.

Images